© 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. 98244
    Prev
    Next
    INDEX
    Explanations

    names of characters and locations in a fantasy context

    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
    sie
    -0.07
    agra
    -0.07
    enger
    -0.06
    .mods
    -0.06
    duk
    -0.06
    .scal
    -0.06
    ýš
    -0.06
    æ¯Ľ
    -0.06
     vit
    -0.06
    éĸĵ
    -0.06
    POSITIVE LOGITS
     Belt
    0.07
    utherland
    0.07
    NECT
    0.06
    airo
    0.06
    rio
    0.06
    à¸ļà¸Ĺ
    0.06
    orate
    0.06
    etas
    0.06
     himself
    0.06
    GMT
    0.06
    Activations Density 0.017%

    No Known Activations