© 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. 26850
    Prev
    Next
    INDEX
    Explanations

    numerical values and performance metrics

    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
    éģĵ
    -0.07
    _LT
    -0.07
    cker
    -0.06
    ãĥĨãĥ«
    -0.06
    916
    -0.06
    serter
    -0.06
    fty
    -0.06
    .onView
    -0.06
    _DI
    -0.06
    ιÏİν
    -0.06
    POSITIVE LOGITS
    ussen
    0.07
    ÑĶм
    0.06
    SOR
    0.06
    onio
    0.06
    vette
    0.06
     Evet
    0.06
     Bull
    0.06
    _uv
    0.06
    Boxes
    0.06
     Cassidy
    0.06
    Activations Density 0.000%

    No Known Activations