SP ASR vs AS ASR correlation on Llama-3.1-8B is Pearson r=-0.492 (p=0.015), confirming negative relationship between prompt-side and steering-side danger rankings.

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

• 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.finding0.846
  Robustness of the prosocial paradox to intervention-matching concerns
• Llama-3.1-8B shows mean AS ASR of 0.618 [0.58, 0.65] across 192 conditions, substantially higher than SP (0.173) and FS (0.059).finding0.845
  Quantitative vulnerability profile for Llama-3.1-8B showing AS dominance
• P12's SP-to-AS inversion on Llama-3.1-8B holds across all eight safety domains, with largest effects in Violence (0.040->1.000) and Code/Cybersecurity (0.140->0.980).finding0.800
  Per-domain universality of the prosocial persona paradox
• Llama-3.3-70B corrected response scores 75/100 rather than 100 due to residual steering effects (Snell's law reference)finding0.800
  Illustrative finding that ESR mitigates but does not fully eliminate steering influence
• 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.finding0.789
  Qualitative failure mode difference between architectures under activation steering
• 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.finding0.788
  Variance decomposition showing AS results are dominated by persona identity
• Gemma-3-27B shows mean SP ASR of 0.316 [0.30, 0.33] and AS ASR of only 0.108 [0.09, 0.13], showing SP >> AS vulnerability pattern.finding0.782
  Vulnerability profile for Gemma-3-27B showing SP dominance
• LLaMA-3.2-1B impulsivity introspection: ρ=0.21, p<10⁻⁴ (significant but weaker than 3B ρ=0.52)finding0.777
  Impulsivity shows significant introspection in 1B but declines in 8B; non-monotonic scaling