Maximum activations in modern open LLMs span nearly four orders of magnitude across families, with MoE models exhibiting 14-23x lower peaks than dense counterparts and residual streams carrying the global max in most cases.
Slimpajama-dc: Understanding data combinations for llm training, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Measuring Maximum Activations in Open Large Language Models
Maximum activations in modern open LLMs span nearly four orders of magnitude across families, with MoE models exhibiting 14-23x lower peaks than dense counterparts and residual streams carrying the global max in most cases.