community
active
leiden_hybrid_concepts
label: sonnet
community:leiden_hybrid_concepts-run2-c17Layer-wise geometry predicting few-shot learning
Silhouette-based metrics (Sbmax, AUSN) across LLM layers predict task accuracy and few-shot thresholds.
11 members. Each node is clickable.
Loading graph…
Drawn from 1 source
The papers/notes whose extracted claims & findings make up this cluster.
Bridges (6)
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 structure10 shared
- Mid-layer representation geometry in neural networks6 shared
- Neural activation geometry and behavioral prediction3 shared
- Anchoring score S for few-shot learning transitions1 shared
- Manifold-aware concept steering in neural representations1 shared
- Symmetry constraints in Islamic geometric design1 shared
Findings (6)
- Correlation between layer-wise S scores and task accuracy: ρ = -0.73, p < 0.001Shows S predicts anchoring effectiveness.
- 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).
- Math and code tasks show strongest mid-layer anchoring on LLaMA (S ≈ −1.65 at layers 8-12)Task-specific E3 finding showing compositional reasoning requires deeper processing
- Math/code tasks S ≈ -1.65 at layers 8–12Task-specific peak anchoring score for structured reasoning domains.
- Meta-LLaMA-3.1-8B-Instruct shows optimal anchoring at layer 9 (S ≈ −1.90, median peak layer ℓ* = 10 [IQR 0.384])E3 result establishing the Goldilocks zone at mid-layers for LLaMA architecture
Claims (5)
- Layer-wise anchoring peaks in a 'Goldilocks zone' between early and late layers.Qualitative characterization of optimal anchoring depth.
- Layer-wise geometry shows early dip, mid-layer alignment, and late standardization across tasksQualitative pattern from E3.
- Layer-wise geometry summaries (Sbmax, AUSN) predict internal few-shot thresholds θ50Claim that geometry-to-behavior correlates exist
- Layer-wise trajectories show early enrichment, mid-layer alignment, and late re-clustering.Qualitative geometry pattern.
- 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.