Interest probe score drifts positively across turns: LMM slope=0.005, p=4.12×10⁻¹⁴ in LLaMA-3.2-3B

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

• 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 scalefinding0.859
  Internal-state drift generalizes across scales; normalized drift also increases significantly with log(model size)
• 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 scalefinding0.815
  Unlike probe drift, report drift magnitude does not follow a clean scaling law; size-slope is negative
• Wellbeing same-concept steering: LMM alpha slope=0.19, focus=0.40, interest=0.25, impulsivity=0.067 in LLaMA-3.2-3Bfinding0.812
  Quantifies per-concept effect size of same-concept steering on self-report
• Impulsivity→interest steering: probe entropy increases (LMM slope=0.024, p=2.30×10⁻⁴) but report entropy does not (p=0.11)finding0.790
  Evidence of a bottleneck between richer internal variation and final report distribution in impulsivity→interest condition
• Interest probe: peak Cohen's d=1.67 (layer 14), p=9.45×10⁻⁶ in LLaMA-3.2-3Bfinding0.789
  Probe validation result confirming interest direction captures meaningful structure
• Interest concept: Spearman ρ=0.76, isotonic R²=0.54 between logit self-report and probe score in LLaMA-3.2-3B (n=400)finding0.783
  Strongest pooled introspective coupling across the four emotive concepts in the primary model
• LLaMA-3.1-8B-Instruct wellbeing introspection: ρ=0.93, isotonic R²=0.90 (LMM probe slope p<10⁻¹⁰)finding0.767
  Near-ceiling introspective performance for wellbeing concept in 8B model; nearly deterministic probe-report relationship
• Same-concept steering shifts self-report monotonically for all four concepts: LMM alpha slopes 0.067–0.40, all p<10⁻¹²finding0.764
  Causal confirmation that coupling between self-report and internal state is genuine; steering toward positive pole increases report