ACROS induces explicit sense representations in frozen decoder LMs via gated residual addition, enabling competitive zero-shot WSD, lexical steering, and cross-lingual adaptation on SmolLM2-360M while preserving base quality.
hub
Improving steering vectors by targeting sparse autoencoder features.arXiv preprint arXiv:2411.02193
11 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
11
Pith papers citing it
1
external citations · external index
hub tools
verdicts
UNVERDICTED 11representative citing papers
LLM tasks are supported by multiple distinct circuits rather than unique mechanisms, demonstrated via Overlap-Aware Sheaf Repulsion and the Distributive Dense Circuit Hypothesis.
RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
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.
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.
Multilingual SAEs strengthen cross-lingual representations for reliable steering and an intersection-based rule selects effective layers without exhaustive search.
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
The Cylindrical Representation Hypothesis (CRH) models LLM representations as a central axis for concept activation surrounded by a normal plane containing sensitive sectors that determine steering sensitivity and introduce intrinsic uncertainty.
SAEExplainer applies activation-guided preference optimization in two iterative rounds to improve explanations of SAE features and reduce hallucinations.
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.
citing papers explorer
-
Sense Representations Are Inducible Interfaces
ACROS induces explicit sense representations in frozen decoder LMs via gated residual addition, enabling competitive zero-shot WSD, lexical steering, and cross-lingual adaptation on SmolLM2-360M while preserving base quality.
-
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
LLM tasks are supported by multiple distinct circuits rather than unique mechanisms, demonstrated via Overlap-Aware Sheaf Repulsion and the Distributive Dense Circuit Hypothesis.
-
RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
-
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.
-
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.
-
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
Multilingual SAEs strengthen cross-lingual representations for reliable steering and an intersection-based rule selects effective layers without exhaustive search.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
The Cylindrical Representation Hypothesis for Language Model Steering
The Cylindrical Representation Hypothesis (CRH) models LLM representations as a central axis for concept activation surrounded by a normal plane containing sensitive sectors that determine steering sensitivity and introduce intrinsic uncertainty.
-
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
SAEExplainer applies activation-guided preference optimization in two iterative rounds to improve explanations of SAE features and reduce hallucinations.
-
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.
-
ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.