Decomposing Refusal Steering in Mixture-of-Experts Models

Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse harmful or disallowed requests. Recent work has shown that a steering vector can be applied to a dense LLM during inference to suppress refusal behavior and induce responses to harmful requests. We extend this refusal steering method to three open-source Mixture-of-Experts (MoE) LLMs to decompose and better understand how refusal mechanisms operate across MoE components. We find that steering performance is uninhibited by the complex routing patterns inherent to the MoE architecture, and that a single expert recovers 78% of the full steering effect on average when free to sel...

<iframe src="https://silytics.si/embed/item/37dbbb49-90d0-4937-b5ec-a49028b76bea" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.