record state
frontier-ownedReview status
This finding is part of accepted frontier state. Review events, reviewable changes, and proof state explain how it can change.
unreviewed
frontiers / frontier
Finding bundle
back to staterecord state
frontier-ownedThis finding is part of accepted frontier state. Review events, reviewable changes, and proof state explain how it can change.
finding statement
finding typeNo entity list is declared.
evidence
source-boundtheoretical · manual state transition
proof impact
packet context1 reviewable changes and 0 evaluation records are attached to this finding id.
Evidence and conditions
method
manual state transition
evidence type
theoretical
conditions
Provenance
source title
Quantifying LLM Attention-Head Stability (2026)
authors
reviewer:will-blair
Attention heads in transformers exhibit bimodal stability: middle layers show <40% seed-consistent head mappings despite identical optimizer/architecture, while early and late layers exceed 70% stability, directly contradicting universality claims for circuits derived from single model instances.
vs_bd3d16868b182c1d · manual_curation
outgoing
vf_841cfc4181456ee4Attention head stability findings (index 1) directly ground the prediction that residual-level circuits provide more robust discovery ground (index 5); cannot claim residual universality without first resolving head instability.
incoming
events
vev_7b3e7e963f0a0bdafinding.assertedManual finding added to frontier state
reviewer:will-blair · 2026-05-29
reviewable changes
vpr_783bb6120c52239ffinding.addManual finding added to frontier state
applied · reviewer:will-blair · 2026-05-29
evaluations
No evaluation record targets this finding id.