In LLaMA-3-8B-Instruct, addition information becomes linearly decodable in a fixed layer-wise order: formula structure, carries and sums, result digits, then output generation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs
In LLaMA-3-8B-Instruct, addition information becomes linearly decodable in a fixed layer-wise order: formula structure, carries and sums, result digits, then output generation.