© 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 EvalsExportsAPI 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. 82935
    Prev
    Next
    INDEX
    Explanations

    terms related to awards and recognition in a professional 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
    pec
    -0.06
    emd
    -0.06
    our
    -0.06
    /un
    -0.06
    ÑĢод
    -0.06
    ingly
    -0.06
    iple
    -0.06
     Dar
    -0.06
     odp
    -0.06
    -f
    -0.06
    POSITIVE LOGITS
    tz
    0.08
    dik
    0.08
    lsi
    0.07
     vur
    0.07
    _totals
    0.07
    usto
    0.07
     vX
    0.07
     lesbi
    0.07
    oleÄį
    0.07
    ,");↵
    0.06
    Activations Density 0.003%

    No Known Activations