© 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. 9-LLAMASCOPE-RES-131K
    11. 94211
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts and physical actions in sports contexts

    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
    arih
    -0.06
    uw
    -0.06
    ende
    -0.06
     Rein
    -0.06
    ova
    -0.06
    ómo
    -0.06
    ;amp
    -0.06
    λα
    -0.06
    DataTask
    -0.06
    reck
    -0.06
    POSITIVE LOGITS
    ubah
    0.07
    ιÏĥ
    0.06
    ORED
    0.06
    alty
    0.06
    bakan
    0.06
     Gent
    0.06
    .IsChecked
    0.06
    ocre
    0.06
    ored
    0.06
    DataContract
    0.06
    Activations Density 0.001%

    No Known Activations