Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

• URL: http://arxiv.org/abs/2605.29358v1
• Date: Thu, 28 May 2026 04:57:47 GMT
• Title: Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
• Abstract summary: We train sparse autoencoders with up to 34 million features on the model's middle layer residual stream.<n>We find features corresponding to famous entities and locations, as well as more abstract concepts like sarcasm or errors in code.
• Score: 16.049764376014668
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictionary learning methods scale beyond small transformers. We trained sparse autoencoders with up to 34 million features on the model's middle layer residual stream, using scaling laws to guide hyperparameter selection. The resulting features are multilingual and multimodal (generalizing to images despite text-only training), respond to both concrete instances and abstract discussions of concepts, and can be used to steer model behavior in ways consistent with their interpretations. We find features corresponding to famous entities and locations, as well as more abstract concepts like sarcasm or errors in code. We also identify features relevant to ways in which language models might cause harm--including features representing deception, power-seeking, sycophancy, and bias--and show that these causally influence model outputs when manipulated. Additionally, we conduct analyses of feature interpretability, geometry, and computational function. However, significant limitations remain: our suite of features is incomplete, and we lack rigorous methods for evaluating whether our features faithfully capture model computations.

Related papers

• A Variational Framework for Improving Naturalness in Generative Spoken Language Models [52.673912922590866]
  We propose an end-to-end variational approach that automatically learns to encode continuous speech attributes to enhance semantic tokens.<n>Our approach eliminates the need for manual extraction and selection of paralinguistic features.<n>It produces preferred speech continuations according to human raters.
  arXiv  Detail & Related papers  (2025-06-17T17:58:17Z)
• The Complexity of Learning Sparse Superposed Features with Feedback [2.4140387101794283]
  We investigate whether the underlying learned features of a model can be efficiently retrieved through feedback from an agent.<n>We analyze the feedback complexity associated with learning a feature matrix in sparse settings.<n>Our results establish tight bounds when the agent is permitted to construct activations and demonstrate strong upper bounds in sparse scenarios.
  arXiv  Detail & Related papers  (2025-02-08T01:54:23Z)
• Predicting the Performance of Black-box LLMs through Self-Queries [60.87193950962585]
  Large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial.<n>In this paper, we extract features of LLMs in a black-box manner by using follow-up prompts and taking the probabilities of different responses as representations.<n>We demonstrate that training a linear model on these low-dimensional representations produces reliable predictors of model performance at the instance level.
  arXiv  Detail & Related papers  (2025-01-02T22:26:54Z)
• LatentQA: Teaching LLMs to Decode Activations Into Natural Language [72.87064562349742]
  We introduce LatentQA, the task of answering open-ended questions about model activations in natural language.<n>We propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs.<n>Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations.
  arXiv  Detail & Related papers  (2024-12-11T18:59:33Z)
• Disentangling Dense Embeddings with Sparse Autoencoders [0.0]
  Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models. We show that the resulting sparse representations maintain semantic fidelity while offering interpretability.
  arXiv  Detail & Related papers  (2024-08-01T15:46:22Z)
• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models [55.19497659895122]
  We introduce methods for discovering and applying sparse feature circuits.<n>These are causally implicatedworks of human-interpretable features for explaining language model behaviors.
  arXiv  Detail & Related papers  (2024-03-28T17:56:07Z)
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
  We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions. Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
  arXiv  Detail & Related papers  (2023-05-15T17:15:40Z)
• An Understanding-Oriented Robust Machine Reading Comprehension Model [12.870425062204035]
  We propose an understanding-oriented machine reading comprehension model to address three kinds of robustness issues. Specifically, we first use a natural language inference module to help the model understand the accurate semantic meanings of input questions. Third, we propose a multilanguage learning mechanism to address the issue of generalization.
  arXiv  Detail & Related papers  (2022-07-01T03:32:02Z)
• Interpreting Language Models with Contrastive Explanations [99.7035899290924]
  Language models must consider various features to predict a token, such as its part of speech, number, tense, or semantics. Existing explanation methods conflate evidence for all these features into a single explanation, which is less interpretable for human understanding. We show that contrastive explanations are quantifiably better than non-contrastive explanations in verifying major grammatical phenomena.
  arXiv  Detail & Related papers  (2022-02-21T18:32:24Z)

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.