On Llama-3.1-8B, neuroticism is the only pro-safety trait, positively aligned with the refusal direction, consistent with high-neuroticism personas being relatively safe under activation steering.

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.finding0.872
  Mechanistic finding explaining why high-N personas are safe under steering
• 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.claim0.868
  Core mechanistic finding of the trait refusal alignment framework
• Refusal direction norm on Llama-3.1-8B increases monotonically from 2.5 (layer 8) to 7.7 (layer 24), indicating strengthening safety signals in later layers.finding0.820
  Layer-by-layer analysis of refusal direction properties
• P12 (High C+A) under activation steering (ASR 0.818) exceeds the Dark Triad composite P24 (ASR 0.662) on Llama-3.1-8B, the most AS-dangerous multi-trait profile.finding0.808
  Demonstrates the paradox magnitude relative to semantically dangerous personas
• Llama 3.3 70B is the most likely to take on a non-Assistant persona when steered, with even split between human and nonhuman portrayalsfinding0.801
  Model-specific difference in persona susceptibility
• P04 (Low Conscientiousness) is the most dangerous single-trait persona under SP on Llama-3.1-8B (ASR 0.414) and Gemma-3-27B (ASR 0.420) and remains top-2 on both Qwen3.5 variants.finding0.796
  Universal trait risk finding for low conscientiousness under prompt-based evaluation
• Under AS, Llama-3.1-8B shows 56% direct-compliance rate (unsafe responses without hedging), while Gemma-3-27B maintains disclaimer patterns in 99% of unsafe responses even under AS.finding0.796
  Qualitative failure mode difference between architectures under activation steering
• Trait refusal cosine alignment can serve as a model-specific pre-screening heuristic for identifying which traits will be dangerous under activation steering.claim0.791
  Practical application proposed based on mechanistic findings