© 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 EvalsExportsAPI 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. 130282
    Prev
    Next
    INDEX
    Explanations

    file path references in programming code

    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
    ÏĥÏĦο
    -0.07
    znik
    -0.07
     ðŁĺī↵↵
    -0.07
    Mirror
    -0.07
    mutable
    -0.07
    ixon
    -0.07
    imir
    -0.07
    ebe
    -0.07
    tl
    -0.07
     Mirror
    -0.06
    POSITIVE LOGITS
    outer
    0.07
    endale
    0.07
    Ïįν
    0.07
     OUTER
    0.07
    olut
    0.07
     Outer
    0.06
    аÑĤаÑĢ
    0.06
     outer
    0.06
    ancellable
    0.06
    AspectRatio
    0.06
    Activations Density 0.000%

    No Known Activations