HSI: Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models

Abstract: Robust alignment guardrails for LLMs are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass safety alignments and effectively steer model generations towards harmful AI coordination for Llama 2. Our method applies fine-grained interventions at specific model subcomponents, particularly attention heads, using a simple binary choice probing strategy. These interventions then generalise to the open-ended generation setting effectively circumventing safety guardrails. We show that probing single attention heads is more effective than intervening on full layers and intervening on only four attention heads is comparable to supervised fine-tuning. We further show that only a few example completions are needed to compute effective steering directions, which is an advantage over classical fine-tuning. Our findings highlight the shortcomings of current alignment techniques. In addition, our results suggest that, at the attention head level, activations encode fine-grained linearly separable behaviors. Practically, the approach offers a straightforward methodology to steer LLM behaviour, which could be extended to diverse domains beyond safety requiring fine-grained control over the model output. The code and datasets for this study can be found on https://github.com/PaulDrm/targeted_intervention.