© 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. 79348
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Clare."

    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
    eer
    -0.09
    gaard
    -0.08
    marvin
    -0.08
    avanaugh
    -0.07
    .gdx
    -0.07
    615
    -0.07
    /XMLSchema
    -0.07
     addCriterion
    -0.07
    ehler
    -0.07
    ergarten
    -0.07
    POSITIVE LOGITS
    quential
    0.07
    iment
    0.07
    field
    0.07
    mont
    0.07
    sek
    0.07
    lak
    0.06
    ns
    0.06
     moo
    0.06
    ases
    0.06
     Booth
    0.06
    Activations Density 0.003%

    No Known Activations