When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures

Yongzhong Xu

By Callan Zhang · Jun 1, 2026 · Editorial standards →

Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.

Source: arXiv cs.LG