We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test detection and steering across Phi-3-mini-4k (3.8B), Qwen2.5-7B (safety-trained), and Dolphin-Llama-3.1-8B (uncensored).
Detection: All models show AUROC 0.996-1.00 at optimal layers. Uncensored Dolphin matches safety-trained models, demonstrating empathy encoding emerges independent of safety training. Phi-3 probes correlate strongly with EIA behavioral scores (r=0.71, p<0.01). Cross-model probe agreement is limited (Qwen: r=-0.06, Dolphin: r=0.18), revealing architecture-specific implementations despite convergent detection.
Steering: Qwen achieves 65.3% success with bidirectional control and coherence at extreme interventions. Phi-3 shows 61.7% success with similar coherence. Dolphin exhibits asymmetric steerability: 94.4% success for pro-empathy steering but catastrophic breakdown for anti-empathy (empty outputs, code artifacts).
Implications: The detection-steering gap varies by model. Qwen and Phi-3 maintain bidirectional coherence; Dolphin shows robustness only for empathy enhancement. Safety training may affect steering robustness rather than preventing manipulation, though validation across more models is needed.
Feature-Aware Malicious Output Detection and Mitigation
Tianjin University（天津大学）；Meituan Group（美团集团）；Tsinghua University（清华大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；Monash University（莫纳什大学）
