Neural activation geometry and behavioral prediction

Quantifies relationships between layer-wise activation statistics (Sbmax, AUSN) and task performance metrics in LLMs, bridging internal representation geometry to behavioral outcomes.

5 members. Each node is clickable.

Loading graph…

Drawn from 1 source

The papers/notes whose extracted claims & findings make up this cluster.

The Guanyin Protocol: A Framework for Immediately Establishing an Understanding of Both Causality and Compassion in LLM Systems Using Semantic Anchoring5 members

Bridges (2)

Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.

Few-shot anchoring & latent structure5 shared
Layer-wise geometry predicting few-shot learning3 shared

Findings (4)

AUSN mean -2.119 ± 0.198Normalized area under S(ℓ) averaged over seeds.
Larger Sbmax associated with smaller θ50 in E3 sweepGeometry-to-behavior correlate within E3.
LLaMA-3.1-8B: Sbmax = -1.896 ± 0.211, AUSN = -2.119 ± 0.198, peak layer ℓ* = 10 (median)Seed-pooled geometry-only statistics (per-dev z units).
Sbmax mean -1.896 ± 0.211Geometry summary peak anchoring score averaged over seeds.

Claims (1)

Peak anchoring Sbmax and normalized area AUSN correlate with per-item success and internal shot midpoints θ50, providing a geometry-to-behavior bridge.Main interpretation of E3.