© 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. 41406
    Prev
    Next
    INDEX
    Explanations

    bibliographic references and citations

    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
     consect
    -0.07
    anie
    -0.07
    lama
    -0.07
    å©
    -0.07
    uhan
    -0.07
    993
    -0.07
    .sponge
    -0.07
    Ế
    -0.07
    atica
    -0.06
    uchar
    -0.06
    POSITIVE LOGITS
    ISBN
    0.07
     disagreement
    0.06
    erot
    0.06
    ubo
    0.06
    inning
    0.05
    /Library
    0.05
     ISBN
    0.05
    oles
    0.05
     QQ
    0.05
    qq
    0.05
    Activations Density 0.004%

    No Known Activations