Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages

• URL: http://arxiv.org/abs/2507.11230v2
• Date: Tue, 29 Jul 2025 13:09:21 GMT
• Title: Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages
• Authors: Lyzander Marciano Andrylie, Inaya Rahmanisa, Mahardika Krisna Ihsani, Alfan Farizki Wicaksono, Haryo Akbarianto Wibowo, Alham Fikri Aji,
• Abstract summary: Existing studies often focus on individual neurons, but their polysemantic nature makes it difficult to isolate language-specific units.<n>We introduce SAE-LAPE, a method based on feature activation probability, to identify language-specific features within the feed-forward network.<n>These features influence the model's multilingual performance and language output and can be used for language identification with performance comparable to fastText.
• Score: 11.19692440351977
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic nature makes it difficult to isolate language-specific units from cross-lingual representations. To address this, we explore sparse autoencoders (SAEs) for their ability to learn monosemantic features that represent concrete and abstract concepts across languages in LLMs. While some of these features are language-independent, the presence of language-specific features remains underexplored. In this work, we introduce SAE-LAPE, a method based on feature activation probability, to identify language-specific features within the feed-forward network. We find that many such features predominantly appear in the middle to final layers of the model and are interpretable. These features influence the model's multilingual performance and language output and can be used for language identification with performance comparable to fastText along with more interpretability. Our code is available at https://github.com/LyzanderAndrylie/language-specific-features

Related papers

• The Emergence of Abstract Thought in Large Language Models Beyond Any Language [95.50197866832772]
  Large language models (LLMs) function effectively across a diverse range of languages.<n>Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts.<n>Recent results show strong multilingual performance, even surpassing English performance on specific tasks in other languages.
  arXiv  Detail & Related papers  (2025-06-11T16:00:54Z)
• Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders [41.1110443501488]
  We introduce a novel metric to assess the monolinguality of features obtained from SAEs.<n>We show that ablating these SAE features only significantly reduces abilities in one language of LLMs, leaving others almost unaffected.<n>We leverage these SAE-derived language-specific features to enhance steering vectors, achieving control over the language generated by LLMs.
  arXiv  Detail & Related papers  (2025-05-08T10:24:44Z)
• Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages [15.203789021094982]
  In large language models (LLMs), how are multiple languages learned and encoded?<n>We train sparse autoencoders on Llama-3-8B and Aya-23-8B, and demonstrate that abstract grammatical concepts are often encoded in feature directions shared across many languages.
  arXiv  Detail & Related papers  (2025-01-10T21:18:21Z)
• How Do Multilingual Language Models Remember Facts? [50.13632788453612]
  We show that previously identified recall mechanisms in English largely apply to multilingual contexts.<n>We localize the role of language during recall, finding that subject enrichment is language-independent.<n>In decoder-only LLMs, FVs compose these two pieces of information in two separate stages.
  arXiv  Detail & Related papers  (2024-10-18T11:39:34Z)
• Lens: Rethinking Multilingual Enhancement for Large Language Models [70.85065197789639]
  We propose Lens, a novel approach to enhance multilingual capabilities in large language models (LLMs)<n>Lens operates on two subspaces: the language-agnostic subspace, where it aligns target languages with the central language to inherit strong semantic representations, and the language-specific subspace, where it separates target and central languages to preserve linguistic specificity.<n>Lens significantly improves multilingual performance while maintaining the model's English proficiency, achieving better results with less computational cost compared to existing post-training approaches.
  arXiv  Detail & Related papers  (2024-10-06T08:51:30Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations [38.56175462620892]
  Large pretrained multilingual language models (ML-LMs) have shown remarkable capabilities of zero-shot cross-lingual transfer. We present a novel view of projecting away language-specific factors from a multilingual embedding space. We show that applying our method consistently leads to improvements over commonly used ML-LMs.
  arXiv  Detail & Related papers  (2024-01-11T09:54:11Z)
• Robust Open-Set Spoken Language Identification and the CU MultiLang Dataset [2.048226951354646]
  Open-set spoken language identification systems can detect when an input exhibits none of the original languages. We implement a novel approach to open-set spoken language identification that uses MFCC and pitch features. We present a spoken language identification system that achieves 91.76% accuracy on trained languages and has the capability to adapt to unknown languages on the fly.
  arXiv  Detail & Related papers  (2023-08-29T00:44:27Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [73.06435180872293]
  We construct a recurrent neural network predictor based on byte embeddings and convolutional layers. We show that some features from various linguistic types can be predicted reliably.
  arXiv  Detail & Related papers  (2020-04-30T21:00:53Z)
• Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations [83.27475281544868]
  We use singular vector canonical correlation analysis to study what kind of information is induced from each source. We observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
  arXiv  Detail & Related papers  (2020-04-30T16:25:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.