SEP 4, 2026 · PREPRINT
How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing
arXiv
A mechanistic, exploratory analysis of internal model behaviour in a large language model using post-hoc interventions; raises questions about stream routing and mixing rather than testing a clinical or validated performance hypothesis.
Reported
Effective stream count per blockapproximately two
C4 perplexity increase (late mixe…1.9%
C4 perplexity increase (early mix…41%