Skip to content

canopusrecord engine body

field
frontiers
loop
body
docs

vela-science/vela

frontier

open-transformer-circuit-evidence

evidence

vea_268a988ac280ef54

resultsread-only vieweressays

Search Canopus

Jump to a section, signal, campaign, document, primitive, work path, frontier, record index, atlas, constellation, agent, capability, or full-state search.

frontiers / frontier

Open-transformer circuit evidence

CC-BY-4.0vfr_c94f4f79b4e341ad

id: vfr_c94f4f79b4e341ad
license: CC-BY-4.0
findings: 42
accepted core: 14
contested: 0

42

findings

6

links

22

sources

42

evidence

0

contested

0.73

avg conf

recordoverview state sources proofenginereviewbodygraph

Evidence atom

back to sources

What determines the layer depth at which specific circuit motifs (e.g., composition, memorization, in-context learning) emerge during training, and does this emergence order remain invariant across model scales (7B→70B) and architectures (Transformer→Mamba)?

id: vea_268a988ac280ef54
frontier: Open-transformer circuit evidence
source: vs_b8a04f98c5991ecb
finding: vf_b10bdbb1f34c381e

evidence boundary

unknown

theoretical

An evidence atom is an inspectable support unit. It is not a finding by itself; it supports or challenges a finding through review.

finding binding

observational

What determines the layer depth at which specific circuit motifs (e.g., composition, memorization, in-context learning) emerge during training, and does this emergence order remain invariant across model scales (7B→70B) and architectures (Transformer→Mamba)?

inspect finding →

source binding

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence (2025); Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures (2024)

vs_b8a04f98c5991ecb

inspect source →

review context

unverified

1 events

1 reviewable changes and 0 evaluation records target this atom or its bound objects.

Evidence statement

What determines the layer depth at which specific circuit motifs (e.g., composition, memorization, in-context learning) emerge during training, and does this emergence order remain invariant across model scales (7B→70B) and architectures (Transformer→Mamba)?

extraction method

manual_curation

support relation

unknown

condition refs

vcnd_ff1b74938de10f0a

Caveats

missing evidence locator

Review, event, and evaluation records

2

events

vev_de90a7f815d80f2cfinding.asserted
Manual finding added to frontier state
reviewer:will-blair · 2026-05-29

reviewable changes

vpr_9af0bb7627f281dbfinding.add
Manual finding added to frontier state
applied · reviewer:will-blair · 2026-05-29

evaluations

No evaluation rows are attached.