Linear probes of Llama activations show an abstraction gradient, but the 70B model deviates with double peaks and anti-persistent adjacent-layer attention.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Emergent effects of scaling on the functional hierarchies within large language models
Linear probes of Llama activations show an abstraction gradient, but the 70B model deviates with double peaks and anti-persistent adjacent-layer attention.