© 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. 17-LLAMASCOPE-RES-131K
    11. 15506
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols used for formatting or separation

    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
    ;/*
    -0.07
     arch
    -0.06
    achs
    -0.06
     Pied
    -0.06
     Epoch
    -0.06
    ESA
    -0.06
    .Invariant
    -0.06
     suppress
    -0.06
     Rodgers
    -0.06
    PLUS
    -0.06
    POSITIVE LOGITS
    borg
    0.07
     Note
    0.07
    note
    0.06
    ToObject
    0.06
    Consult
    0.06
    warz
    0.06
     Consult
    0.06
    ffield
    0.06
     each
    0.06
    oba
    0.06
    Activations Density 0.067%

    No Known Activations