REVIEW 14 cited by
Steering Large Language Model Activations in Sparse Spaces
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Steering Large Language Model Activations in Sparse Spaces
read the original abstract
A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior work in dense activation spaces struggles with superposition, wherein multiple features become entangled, limiting interpretability and precise control. In contrast, sparse representations provide an untapped opportunity for more interpretable behavior modulation. In this work, we introduce sparse activation steering (SAS), a method that leverages sparse autoencoders (SAEs) to steer LLM behavior in sparse spaces. By isolating behavior-specific features through a contrastive prompt-pairing approach, we define a set of features that can selectively reinforce or suppress behaviors. Experiments on Gemma 2 LLMs show that SAS vectors enable nuanced behavioral modulation and finer-grained control. Furthermore, scaling SAEs improves monosemanticity of SAS vectors, suggesting more reliable and interpretable interventions.
Forward citations
Cited by 14 Pith papers
-
Tapered Language Models
Tapered Language Models monotonically decrease MLP width across depth with a cosine schedule, yielding better perplexity and downstream performance than uniform-width baselines across multiple architectures and scales...
-
LLM Self-Recognition: Steering and Retrieving Activation Signatures
Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
-
Perplexity Can Miss SAE Feature Damage Under Quantization
Quantization of LLMs can degrade many SAE features even when perplexity improves or stays similar, as shown by correlation measurements on frozen SAEs for Pythia-70M and Gemma-2-2B models across INT8 to INT4.
-
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
LRS trains a latent reward model on final-answer correctness to steer SAE states during inference, improving reasoning performance and implicitly encouraging better cognitive behaviors.
-
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Reward-guided optimization of SAE latents, gated by reward and confidence, improves multi-benchmark reasoning and is post-hoc associated with more verification and course correction.
-
Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
Activation steering produces synthetic safety-violating data that improves downstream classifiers over prompting on most tested concepts when a harmonic mean of alignment, coherence, and diversity is optimized.
-
Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
Mechanism design leaves a strictly positive welfare loss under incomplete contracts, but prosocial LLM agents close the gap in resource allocation and social dilemma settings.
-
Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
Mechanism design leaves a strictly positive welfare loss under incomplete contracts for AI agents, but prosocial agents close this gap and improve social welfare.
-
Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models
PAS automates activation steering for LLMs using labeled data to improve behavior control on tasks like bias and alignment, with gains over ICL and SFT but limited effect on intelligence tasks.
-
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
VS2 constructs steering vectors from sparse SAE features on unlabeled in-domain activations to improve zero-shot accuracy of CLIP models by 0.93-4.12% on CIFAR-100, CUB-200, and Tiny-ImageNet while remaining forward-p...
-
Steered Generation via Gradient-Based Optimization on Sparse Query Features
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
-
A Systematic Study of Training-Free Methods for Trustworthy Large Language Models
Training-free methods for LLM trustworthiness show inconsistent results across dimensions, with clear trade-offs in utility, robustness, and overhead depending on where they intervene during inference.
-
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.
-
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
Qwen-Scope provides open-source sparse autoencoders for Qwen models that function as practical interfaces for steering, evaluating, data workflows, and optimizing large language models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.