Extending Activation Steering to Broad Skills and Multiple Behaviours
read the original abstract
Current large language models have dangerous capabilities, which are likely to become more problematic in the future. Activation steering techniques can be used to reduce risks from these capabilities. In this paper, we investigate the efficacy of activation steering for broad skills and multiple behaviours. First, by comparing the effects of reducing performance on general coding ability and Python-specific ability, we find that steering broader skills is competitive to steering narrower skills. Second, we steer models to become more or less myopic and wealth-seeking, among other behaviours. In our experiments, combining steering vectors for multiple different behaviours into one steering vector is largely unsuccessful. On the other hand, injecting individual steering vectors at different places in a model simultaneously is promising.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
FishBack derives a closed-form minimum-distortion steering direction from the pullback Fisher metric of the softmax layer, outperforming Euclidean baselines on GPT-2 verb-morphology tasks with lower off-target KL divergence.
-
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
GCAD reduces coherence drift from -18.6 to -1.9 and raises turn-10 trait expression from 78.0 to 93.1 in persona-steering tasks by using gated attention-delta interventions from system prompts.
-
Steer Like the LLM: Activation Steering that Mimics Prompting
PSR models that estimate token-specific steering coefficients from activations outperform standard activation steering and compare favorably to prompting on steering benchmarks.
-
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics...
-
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
GCAD steering extracts prompt-based attention deltas and gates them at token level, cutting coherence drift from -18.6 to -1.9 while raising trait expression at turn 10 from 78 to 93 on multi-turn persona benchmarks.
-
Contextual Linear Activation Steering of Language Models
CLAS dynamically adapts linear activation steering strengths to context, outperforming fixed-strength steering and matching or exceeding ReFT and LoRA on eleven benchmarks across four model families with limited labeled data.
-
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
The Master Key Hypothesis states that capabilities are low-dimensional directions transferable across models through linear subspace alignment, with UNLOCK demonstrating gains such as 12.1% accuracy improvement on MAT...
-
Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering
Introduces multitask RepE to improve readability of LLM-generated code while analyzing the tradeoff with correctness via theory and experiments.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.