ScoringModel raises mean Recall@10 to 52.2 on the FakeWiki provenance benchmark from 35.0 for the best baseline, winning 41 of 45 model-by-condition comparisons and gaining 15.7 points on jailbreak-style queries.
Extracting latent steering vectors from pretrained language models.arXiv preprint arXiv:2205.05124
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
Llama-3.1-8B computes sums for cyclic concepts using base-10 addition via task-agnostic Fourier features with periods 2, 5, and 10 rather than modular arithmetic in the concept period.
Early hidden state features from the first few tokens allow a GBDT classifier to predict activation steering success, under-steering, or over-steering with 0.7 macro-F1 on unseen concepts.
Steering Dark Triad features in an LLM increases exploitative and aggressive behavior while leaving strategic deception and cognitive empathy unchanged, indicating dissociable antisocial pathways.
Pairwise matrices for SAEs demonstrate that single-feature inspection mislabels causal axes, with joint suppression and matched-geometry controls revealing distinct output regimes not captured by single-feature or random perturbations.
Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.