finding
active
finding:icl-dynamics-on-llama-3-1-8b-are-sigmoidal-in-n-1-fit-by-power-law-discounted-likelihoodICL dynamics on Llama-3.1-8B are sigmoidal in N^{1-α}, fit by power-law-discounted likelihood
Prediction 1 confirmed.
Source paper
extracted_from(2025) · Eric Bigelow · Daniel Wurgaft · YingQiao Wang · Noah D. Goodman +3
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Justifies discount τ(N)=N^{-α}.
Hypotheses (1)
hypothesis
- Prediction 1: p(y(c)|x) follows a sigmoid as N^{1-α} accumulatesassociated_withsupportsFrom Eq. 5.
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.
- Scale test.
- App. E.
- Llama-3.3-70B exhibits internal consistency-checking mechanisms that operate during inferenceclaim0.778Central interpretive claim of the paper supported by causal ablation and activation evidence
- The specific Fourier feature periods identified confirm base-10 rather than modular computation
- Demonstrates that small models represent surface features rather than abstract truth
- Empirical observation establishing that Llama's behavior for days-of-week tasks has circular structure.
- Supporting finding showing ESR is driven by both higher multi-attempt rates and comparable improvement rates
- At Llama layer 26 (~81% depth) the predictive component does not dominate the latent norm.finding0.760Fig. 14.