© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 38440
    Prev
    Next
    INDEX
    Explanations

    references to violations and their consequences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     somehow
    -0.08
    som
    -0.06
    ajas
    -0.06
     Alley
    -0.05
    ĥ½
    -0.05
     diss
    -0.05
     Virgin
    -0.05
    ÑĨев
    -0.05
     al
    -0.05
     somewhat
    -0.05
    POSITIVE LOGITS
     except
    0.12
    except
    0.12
     кÑĢоме
    0.12
    _except
    0.10
     Except
    0.10
    Except
    0.09
     NOTHING
    0.09
     Done
    0.08
     Nothing
    0.08
     happens
    0.08
    Activations Density 0.031%

    No Known Activations