Wellbeing probe-score drift across turns significant at all three LLaMA scales (slopes=0.006, 0.005, 0.013 for 1B, 3B, 8B; all p<10⁻¹⁰); drift magnitude increases with scale

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

• Interest probe score drifts positively across turns: LMM slope=0.005, p=4.12×10⁻¹⁴ in LLaMA-3.2-3Bfinding0.859
  Demonstrates genuine internal-state dynamics in LLMs during multi-turn conversation
• Wellbeing probe drift is positive in Gemma (ρ=0.34 pooled turn-correlation) and Qwen (ρ=0.24); both p<10⁻⁵finding0.859
  Normalized probe-score drift across turns generalizes beyond LLaMA family
• Logit self-report drift positive for all three LLaMA sizes (turn slopes 0.159, 0.038, 0.141; all p<10⁻²⁰) but does not increase monotonically with scalefinding0.844
  Unlike probe drift, report drift magnitude does not follow a clean scaling law; size-slope is negative
• LLaMA-3.1-8B-Instruct wellbeing introspection: ρ=0.93, isotonic R²=0.90 (LMM probe slope p<10⁻¹⁰)finding0.837
  Near-ceiling introspective performance for wellbeing concept in 8B model; nearly deterministic probe-report relationship
• Wellbeing same-concept steering: LMM alpha slope=0.19, focus=0.40, interest=0.25, impulsivity=0.067 in LLaMA-3.2-3Bfinding0.837
  Quantifies per-concept effect size of same-concept steering on self-report
• Wellbeing probe: peak Cohen's d=3.34 (layer 16), p=7.21×10⁻¹³ in LLaMA-3.2-3Bfinding0.827
  Probe validation result confirming wellbeing direction captures meaningful structure
• Wellbeing introspective strength at turn 1: ρ=0.52, p=5.46×10⁻⁴ in LLaMA-3.2-3Bfinding0.814
  Demonstrates introspection is present from the first conversation turn without needing multi-turn context
• Wellbeing concept: Spearman ρ=0.68, isotonic R²=0.48 in LLaMA-3.2-3B (n=400, p<10⁻²⁶)finding0.791
  Second-strongest pooled introspective coupling in primary model