Llama-3.1 8B

Primary substrate for experiments; language model used to validate manifold steering on days-of-week, months, letters, ages.

Neighborhood — ranked by edge-count

paper

community

method

Next-Day Arithmetic Task
uses
The evaluation task used to probe Llama's representation of days of the week: questions of the form 'What day comes N days after X?'

finding

manifold steering produces clean probability shifts along natural behavior structure; linear steering cuts across manifold and produces off-target noisy effects
about
Empirical demonstration on Llama-3.1-8B that steering along representation manifold aligns outputs with behavior manifold, whereas linear steering does not.

venue

arXiv:2605.05115
cites
Publication venue for Wurgaft et al. manifold steering paper.

institute

Goodfire
studies
AI research company; authors' affiliation; develops tools including EVEE and publishes research on genomic foundation models.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

LLaMA3.1-8Bconcept0.952
One of four LLMs selected for representation analysis; embedding dimension D=4096; used as demonstration model in scatter plots.
LLaMA 3.3 70Bconcept0.907
The model used in Experiment 2 for SAE feature steering experiments via Goodfire API
LLaMA3.1-70Bconcept0.904
One of four LLMs selected; larger model with D=8192 embedding dimension; analyzed across proportionally aligned layers.
Llama 3.1 405Bconcept0.900
Large open-weight model showing compliance gap in helpful-only setting
Llama-3.1-8B-Instructconcept0.871
Primary qualitative demonstration model and one of 14 LLMs benchmarked
Meta-Llama-3.1-8B-Instructconcept0.842
Backbone model used in E3 geometry analysis.
Llama-3.2-3B-Instructconcept0.839
3B Llama model tested; used for injection stride visualization
Llama-3.3-70B-Instructconcept0.833
Primary model of interest showing substantial ESR; largest model tested in the study