© 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. 72079
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people's names, particularly those associated with notable actions or events

    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
    upe
    -0.06
    to
    -0.06
    uko
    -0.06
    uffman
    -0.06
     Ekon
    -0.06
    ball
    -0.06
     redeem
    -0.06
    uras
    -0.06
    ÐľÐŀ
    -0.06
    ann
    -0.06
    POSITIVE LOGITS
    ocket
    0.08
    práv
    0.08
    pane
    0.07
    itted
    0.07
    tra
    0.07
    cko
    0.07
    urm
    0.06
    _PUR
    0.06
    shipping
    0.06
    .opensource
    0.06
    Activations Density 0.003%

    No Known Activations