LLaMA E3 geometry summary: S_max = −1.896 ± 0.211, AUS_N = −2.119 ± 0.198, peak layer ℓ* = 10 [IQR 0.384]

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

• LLaMA-3.1-8B: Sbmax = -1.896 ± 0.211, AUSN = -2.119 ± 0.198, peak layer ℓ* = 10 (median)finding0.883
  Seed-pooled geometry-only statistics (per-dev z units).
• Interest probe: peak Cohen's d=1.67 (layer 14), p=9.45×10⁻⁶ in LLaMA-3.2-3Bfinding0.798
  Probe validation result confirming interest direction captures meaningful structure
• The case at approximately the 2/3 layer of LLaMA3.1-8B (Layer 24, satisfying Criteria 1 and 2) aligns with prior studies showing the 2/3 layer optimally predicts human brain activity.finding0.793
  Connects this study's results to Schrimpf et al. 2021 and Caucheteux et al. 2022/2023 findings on brain-LLM alignment.
• Math and code tasks show strongest mid-layer anchoring on LLaMA (S ≈ −1.65 at layers 8-12)finding0.791
  Task-specific E3 finding showing compositional reasoning requires deeper processing
• ESR exhibits non-monotonic relationship with boost level, peaking around -0.3σ below threshold in Llama-3.3-70Bfinding0.780
  Characterizes the narrow operating window in which ESR can manifest
• Systematic layer 20-28 degradation in S(ℓ) to S ≈ −2.40 by layer 27 on LLaMAfinding0.780
  Validates representational drift theory: later layers specialize for next-token prediction, increasing dr
• Factual tasks F0-F3 reach near-perfect AUROC in early-to-mid layers of Llama-3.1-8B; arithmetic tasks A1-A3 emerge much later; counting tasks F4-F5 emerge late similar to arithmetic.finding0.777
  Core empirical finding about layer-dependent truth direction emergence across task types.
• Multi-attempt improvement rate peaks at 83% around -1.0σ below threshold in Llama-3.3-70Bfinding0.776
  Shows slightly weaker steering allows more successful corrections, characterizing optimal ESR conditions