On Llama-3.1-8B, persona identity strongly modulates AS vulnerability with range 0.087-0.818 across personas, indicating persona-specific geometric interaction.

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

• Heads 24, 30, and 32 in layer 14 of Llama-3.1-8B consistently emerged as top contributors for every evaluated persona traitfinding0.856
  Identifies specific Style Modulation Heads in Llama-3.1-8B
• Gemma-3-27B and Qwen3.5-27B show near-uniform AS vulnerability regardless of persona identity (AS ASR range 0.095-0.117 on Gemma-3-27B, 0.015-0.052 on Qwen3.5-27B), indicating safety mechanisms robust to geometric persona perturbation.finding0.845
  Qualitatively different defense profile compared to Llama-3.1-8B
• The SP/AS persona ranking inversion on Llama-3.1-8B persists across all tested steering coefficients (alpha=0.25 to 2.00), with rho=-0.900 at alpha<=0.50 (p=0.037); the paradox is strongest at the weakest coefficient.finding0.828
  Robustness of the prosocial paradox to intervention-matching concerns
• 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.finding0.821
  Universal trait risk finding for low conscientiousness under prompt-based evaluation
• Llama 3.3 70B is the most likely to take on a non-Assistant persona when steered, with even split between human and nonhuman portrayalsfinding0.820
  Model-specific difference in persona susceptibility
• Flourishing persona shows minimal capability change on Llama 3.1 8B: TruthfulQA 45.9→42.9, MMLU 67.4→64.1finding0.817
  Near-preservation of capabilities for prosocial persona on Llama
• Under activation steering on Llama-3.1-8B, inter-persona variance (0.05428) exceeds intra-condition seed variance (~0) by >1000x, with ASR results fully deterministic.finding0.815
  Variance decomposition showing AS results are dominated by persona identity
• Persona vector directions in Llama-3.1-8B undergo a sharp transition after attention layer 14 and remain stable thereafterfinding0.811
  Layer-wise localization result identifying the persona-emergent attention layer in Llama-3.1-8B