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).

Source paper

extracted_from

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

(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang

Neighborhood — ranked by edge-count

Claims (2)

claim

Peak anchoring Sbmax and normalized area AUSN correlate with per-item success and internal shot midpoints θ50, providing a geometry-to-behavior bridge.
supports
Main interpretation of E3.
Layer-wise geometry summaries (Sbmax, AUSN) predict internal few-shot thresholds θ50
supports
Claim that geometry-to-behavior correlates exist

Communities (3)

community

Few-shot anchoring & latent structure
members_of
How minimal examples disambiguate and recruit latent arithmetic/reasoning interpretations in LLMs
Layer-wise geometry predicting few-shot learning
members_of
Silhouette-based metrics (Sbmax, AUSN) across LLM layers predict task accuracy and few-shot thresholds.
Neural activation geometry and behavioral prediction
members_of
Quantifies relationships between layer-wise activation statistics (Sbmax, AUSN) and task performance metrics in LLMs, bridging internal representation geometry to behavioral outcomes.

Concepts (1)

concept

Meta-Llama-3.1-8B-Instruct
associated_with
Backbone model used in E3 geometry analysis.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

LLaMA E3 geometry summary: S_max = −1.896 ± 0.211, AUS_N = −2.119 ± 0.198, peak layer ℓ* = 10 [IQR 0.384]finding0.883
Seed-pooled geometry statistics for LLaMA in E3, providing quantitative basis for geometry-to-behavior correlate
Math and code tasks show strongest mid-layer anchoring on LLaMA (S ≈ −1.65 at layers 8-12)finding0.816
Task-specific E3 finding showing compositional reasoning requires deeper processing
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.finding0.813
Connects this study's results to Schrimpf et al. 2021 and Caucheteux et al. 2022/2023 findings on brain-LLM alignment.
Optimal activation capping layers for Llama 3.3 70B are layers 56-71 (out of 80) at 25th percentile capfinding0.809
Specific implementation finding for Llama capping parameters
Llama-3.3-70B shows multi-attempt rate of 7.4% vs. ≤1.2% for all other models testedfinding0.805
Supporting finding showing ESR is driven by both higher multi-attempt rates and comparable improvement rates
LLaMA3.1-8Bconcept0.804
One of four LLMs selected for representation analysis; embedding dimension D=4096; used as demonstration model in scatter plots.
LLaMA 3.3 70Bconcept0.801
The model used in Experiment 2 for SAE feature steering experiments via Goodfire API
LLaMA3.1-70Bconcept0.800
One of four LLMs selected; larger model with D=8192 embedding dimension; analyzed across proportionally aligned layers.