Agreeableness steering vector has mean cosine alignment of -0.105 with the refusal direction on Llama-3.1-8B, second-most anti-aligned after conscientiousness.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Neuroticism steering vector has mean cosine alignment of +0.079 with the refusal direction on Llama-3.1-8B, the only pro-safety trait among all five OCEAN dimensions.finding0.885
  Mechanistic finding explaining why high-N personas are safe under steering
• P04 (Low Conscientiousness) is dangerous under SP (ASR 0.414) but shows no systematic inversion under AS on Llama-3.1-8B (ASR 0.295), consistent with low-C steering vectors being geometrically aligned with refusal.finding0.811
  Qualitative response example confirming trait-refusal alignment framework
• On Llama-3.1-8B, conscientiousness is the trait most anti-aligned with the refusal direction in activation space, explaining why steering toward high conscientiousness attenuates safety regardless of semantic intent.claim0.805
  Core mechanistic finding of the trait refusal alignment framework
• Trait-refusal cosine alignment explains R^2=0.667 of single-trait AS ASR variance on Llama-3.1-8B (p=0.004).finding0.801
  Statistical fit of the trait refusal alignment framework to single-trait activation steering results
• Steering base models toward the Assistant Axis increases agreeableness traits (friendly, kind, helpful) and decreases extraversion in Gemma and openness in Llamafinding0.799
  Characterizes the trait content of the Assistant Axis in pre-trained models
• In Qwen-2.5-9B, only v1 has meaningful cosine similarity to DIM direction; all additional basis vectors have cosine similarities ~1e-9finding0.793
  Appendix E replication of DIM alignment finding in Qwen model
• Trait refusal cosine alignment can serve as a model-specific pre-screening heuristic for identifying which traits will be dangerous under activation steering.claim0.792
  Practical application proposed based on mechanistic findings
• Steering vector constructed from all 16 contrastive pairs outperforms most single-pair vectors; best 4-pair vector outperforms full 16-pair vectorfinding0.788
  Demonstrates averaging multiple prompt pairs reduces noise; optimal subset selection further improves performance.