© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 97332
    Prev
    Next
    INDEX
    Explanations

    actions related to defensive plays in football

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    .MouseAdapter
    -0.07
    bra
    -0.07
    ÏĢλ
    -0.06
    QT
    -0.06
    é
    -0.06
    κÎŃ
    -0.06
    ÅĻÃŃzenÃŃ
    -0.06
    ëŁī
    -0.06
    acs
    -0.06
    odel
    -0.06
    POSITIVE LOGITS
     credit
    0.07
    folio
    0.07
     Credit
    0.06
    cing
    0.06
     PIE
    0.06
    -force
    0.06
    #
    0.05
    pst
    0.05
     Buchanan
    0.05
    credit
    0.05
    Activations Density 0.011%

    No Known Activations