finding
active
finding:wellbeing-concept-spearman-0-68-isotonic-r2-0-48-in-llama-3-2-3b-n-400-p-10-26Wellbeing concept: Spearman ρ=0.68, isotonic R²=0.48 in LLaMA-3.2-3B (n=400, p<10⁻²⁶)
Second-strongest pooled introspective coupling in primary model
Source paper
extracted_from(2026) · Nicolas Martorell · Bianchi, Bruno
Neighborhood — ranked by edge-count
Claims (1)
claim
- Central practical conclusion; both methods partially track the same latent state but with different failure modes
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Weakest but still significant pooled introspective coupling in primary model
- Strongest pooled introspective coupling across the four emotive concepts in the primary model
- Third-strongest pooled introspective coupling in primary model
- LLaMA-3.1-8B-Instruct wellbeing introspection: ρ=0.93, isotonic R²=0.90 (LMM probe slope p<10⁻¹⁰)finding0.848Near-ceiling introspective performance for wellbeing concept in 8B model; nearly deterministic probe-report relationship
- Strong introspective coupling in Qwen model; demonstrates cross-family generalization of introspective capacity
- Quantifies per-concept effect size of same-concept steering on self-report
- Weaker but still significant introspective coupling in Gemma model; consistent with lower probe quality
- Focus→wellbeing: ρ increases from 0.42 (α=-4) to 0.85 (α=+4); R² from 0.34 to 0.75 in LLaMA-3.2-3Bfinding0.796Scatter plot visualization of the dramatic tightening of probe-report relationship at extreme steering settings