arXiv · 2611.17481
Creating Steering Vectors via Input Optimisation
Abstract
Activation steering influences a language model's behaviour by adding a steering vector to its residual stream during generation, but it requires white-box access to modify the hidden states at every generation step. We introduce ActGCG, a modification of Greedy Coordinate Gradient which optimises a suffix to match the target activations obtained by adding a steering vector to the residual stream. We further introduce universal suffixes trained across many prompts at once, a model-translation step that rewrites the suffix into human-readable text midway through optimisation, and a soft-suffix variant to remove the discrete token space constraint. We study two behaviours: steering a model to answer in German, and anti-refusal steering for jailbreaking. For German, a discrete suffix reproduces the steering vector's behaviour almost perfectly and transfers well across prompts and models. For anti-refusal, the equivalence is weaker, succeeding under a phrase-avoidance metric but only partially under the stricter HarmBench classifier. Our results show that a steering vector's behaviour is reachable from the input, with no access to model internals at generation time, up to a loss that depends on the concept being steered.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Batuhan Akar. 2026-11-12. Creating Steering Vectors via Input Optimisation. https://searcharxiv.com/abs/2611.17481
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.