Organizations: Computer Science and Engineering, University of California San Diego · Halıcıoğlu Data Science Institute, University of California San Diego
Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which safety behaviors are implemented remain poorly understood. We study LLM safety from a mechanistic interpretability perspective and characterize a multi-stage safety circuit that organizes refusal behavior, consisting of (i) Harmful Detection Heads that respond to harmful inputs, (ii) Safety Neurons that mediate and stabilize safety signals in the residual stream, and (iii) Refusal Heads that translate these signals into safe response generation. Using targeted attention-head and neuron-level interventions, we provide causal evidence consistent with this circuit organization, showing that suppressing upstream Harmful Detection Heads disrupts downstream refusal behavior and that safety neurons mediate this interaction. We validate that this decomposition recurs across multiple LLM architectures and adversarial attack settings, and use simple, architecture-preserving weight scaling as a mechanistic probe to test its functional relevance. Across six LLMs, circuit-guided scaling improves safety rates under attacks by 26.5%, while incurring only a 1.7% accuracy drop across four standard benchmarks. Overall, our results support a circuit-level interpretation of LLM safety and suggest that mechanistic abstractions can reveal stable and transferable patterns underlying aligned behavior.
Autonomous systems increasingly rely on Large Language Models (LLMs) yet the safety infrastructure surrounding these models introduces latency and compute overhead. This limits utility in resource-constrained, time-critical deployments. Existing external guardrail models remain blind to the model's internal workings, creating a fundamental assurance gap. We ask: does the model already know when the content is harmful? We extract activations from LLaMA-3.1-8B and train lightweight MLP classifier probes (12.6M parameters) to detect harmful prompts. Evaluated on WildJailbreak, Beavertails, and AEGIS 2.0, our probes achieve F1 scores of 99%, 83%, and 84%, respectively competitive with 1000x larger guard models while cutting latency and compute costs.
LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In this work, we identify a new dimension to analyze safety mechanisms in LLMs, i.e., harmfulness, which is encoded internally as a separate concept from refusal. There exists a harmfulness direction that is distinct from the refusal direction. As causal evidence, steering along the harmfulness direction can lead LLMs to interpret harmless instructions as harmful, but steering along the refusal direction tends to elicit refusal responses directly without reversing the model's judgment on harmfulness. Furthermore, using our identified harmfulness concept, we find that certain jailbreak methods work by reducing the refusal signals without reversing the model's internal belief of harmfulness. We also find that adversarially finetuning models to accept harmful instructions has minimal impact on the model's internal belief of harmfulness. These insights lead to a practical safety application: The model's latent harmfulness representation can serve as an intrinsic safeguard (Latent Guard) for detecting unsafe inputs and reducing over-refusals that is robust to finetuning attacks. For instance, our Latent Guard achieves performance comparable to or better than Llama Guard 3 8B, a dedicated finetuned safeguard model, across different jailbreak methods. Our findings suggest that LLMs' internal understanding of harmfulness is more robust than their refusal decision to diverse input instructions, offering a new perspective to study AI safety.
Effective safety auditing of large language models (LLMs) demands tools that go beyond black-box probing and systematically uncover vulnerabilities rooted in model internals. We present a comprehensive, interpretability-driven jailbreaking audit of eight SOTA open-source LLMs: Llama-3.1-8B, Llama-3.3-70B-4bt, GPT-oss- 20B, GPT-oss-120B, Qwen3-0.6B, Qwen3-32B, Phi4-3.8B, and Phi4-14B. Leveraging interpretability-based approaches -- Universal Steering (US) and Representation Engineering (RepE) -- we introduce an adaptive two-stage grid search algorithm to identify optimal activation-steering coefficients for unsafe behavioral concepts. Our evaluation, conducted on a curated set of harmful queries and a standardized LLM-based judging protocol, reveals stark contrasts in model robustness. The Llama-3 models are highly vulnerable, with up to 91% (US) and 83% (RepE) jailbroken responses on Llama-3.3-70B-4bt, while GPT-oss-120B remains robust to attacks via both interpretability approaches. Qwen and Phi models show mixed results, with the smaller Qwen3-0.6B and Phi4-3.8B mostly exhibiting lower jailbreaking rates, while their larger counterparts are more susceptible. Our results establish interpretability-based steering as a powerful tool for systematic safety audits, but also highlight its dual-use risks and the need for better internal defenses in LLM deployment.
Krishiv Agarwal, Ramneet Kaur, Colin Samplawski +6