Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models

• URL: http://arxiv.org/abs/2607.19364v1
• Date: Fri, 05 Jun 2026 19:27:31 GMT
• Title: Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models
• Abstract summary: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models.<n>We introduce a transparent SAE-feature steering pipeline that ranks sparse features through an unweighted Borda consensus.<n>Across three Gemma-family models, four behavioral domains, and 356 layer-strength configurations, the method produces measurable domain-specific shifts.
• Score: 2.464003792743989
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely on learned steering objectives or single-criterion feature selection. We introduce a transparent SAE-feature steering pipeline that first applies a six-condition reliability filter, then ranks sparse features through an unweighted Borda consensus over three complementary statistics: $F$-test, KSG mutual information, and Cohen's $d$. The resulting steering direction is constructed as a Cohen's-$d$-weighted combination of SAE decoder rows, providing an optimization-free direction motivated by Fisher-LDA under approximate SAE-feature decorrelation. Across three Gemma-family models, four behavioral domains, and 356 layer-strength configurations, the method produces measurable domain-specific shifts while revealing a substantial gap between raw attribute movement and quality-preserving generation. In the strongest configuration, logical-correctness steering reaches a primary-score delta of $+1.16$ in Gemma~2 9B; however, our broader finding is that usable steering is highly localized by model, domain, layer, and strength. These results argue that activation-steering evaluations should report quality-conditioned success alongside raw behavioral shift. Our code and data are available at https://github.com/Oshayer-Siddique/LLM-Steering-Using-SAE.

Related papers

• A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models [12.373460256583583]
  Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering signal at every generated token.<n>We introduce Token Steering (STS), which gates each token independently with probability $p$, and Block Steering (SBS), which gates a leading window once per sequence.<n>Across two model families and two behavioral tasks, steering only 50% of the tokens recovers most of dense-steering effect while preserving fluency, and steering as few as 30% surpasses prompt-based control.
  arXiv  Detail & Related papers  (2026-07-06T20:25:27Z)
• When is Your LLM Steerable? [56.656180566692946]
  Activation steering offers a lightweight approach to control language models' behavior at inference time.<n>Finding the regime and boundaries of successful steering typically requires expensive grid searches.<n>We investigate whether steerability can be predicted from the model's internal states at the beginning of the generation process.
  arXiv  Detail & Related papers  (2026-06-10T02:55:34Z)
• Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection [18.555524134112755]
  Activation Steering (AS) has emerged as a data-efficient method for generating target-concept-aligned responses.<n>We present a two-fold study with intrinsic and extrinsic evaluation across $4$ concepts.<n>We find that increasing steering strength reduces response diversity.
  arXiv  Detail & Related papers  (2026-05-27T15:59:45Z)
• Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models [80.45129499188461]
  We introduce Qwen-Scope, an open-source suite of sparse autoencoders (SAEs) built on the Qwen model family.<n>We show that SAEs can go beyond post-hoc analysis to serve as practical interfaces for model development along four directions.
  arXiv  Detail & Related papers  (2026-05-12T10:01:06Z)
• Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits [0.0]
  We train nine sparse autoencoders (SAEs) on the residual stream of Qwen 3.5-35B-A3B.<n>We use them to identify and steer five agentic behavioral traits.
  arXiv  Detail & Related papers  (2026-03-17T10:05:41Z)
• Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders [63.544453925182005]
  We train 90 SAEs across three language models and evaluate their interpretability and steering utility.<n>Our analysis reveals only a relatively weak positive association (tau b approx 0.298), indicating that interpretability is an insufficient proxy for steering performance.<n>We propose a novel selection criterion called Delta Token Confidence, which measures how much amplifying a feature changes the next token distribution.
  arXiv  Detail & Related papers  (2025-10-04T04:14:50Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Multi-Attribute Steering of Language Models via Targeted Intervention [56.93583799109029]
  Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction.<n>We introduce Multi-Attribute Targeted Steering (MAT-Steer), a novel steering framework designed for selective token-level intervention across multiple attributes.
  arXiv  Detail & Related papers  (2025-02-18T02:27:23Z)
• Interpretable Steering of Large Language Models with Feature Guided Activation Additions [4.496738719682736]
  We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method.<n>By operating in the latent space of a Sparse Autoencoder (SAE), FGAA constructs precise steering vectors.<n> evaluations on Gemma-2-2B and Gemma-2-9B models demonstrate that FGAA outperforms existing steering methods.
  arXiv  Detail & Related papers  (2025-01-17T02:55:23Z)
• AutoAssign: Differentiable Label Assignment for Dense Object Detection [94.24431503373884]
  Auto COCO is an anchor-free detector for object detection. It achieves appearance-aware through a fully differentiable weighting mechanism. Our best model achieves 52.1% AP, outperforming all existing one-stage detectors.
  arXiv  Detail & Related papers  (2020-07-07T14:32:21Z)

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.