© 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. 62444
    Prev
    Next
    INDEX
    Explanations

    parts of text that express feelings of gratitude, admiration, or recognition

    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
    úsqueda
    -0.08
    upply
    -0.08
    rowsable
    -0.08
    yonel
    -0.08
    annels
    -0.08
    eah
    -0.08
    istring
    -0.08
    rá
    -0.08
    odyn
    -0.08
    ontent
    -0.08
    POSITIVE LOGITS
     reactions
    0.08
     rem
    0.08
     comments
    0.07
     sympathy
    0.07
     support
    0.07
     responses
    0.07
     recognition
    0.07
     feedback
    0.06
    a
    0.06
     attention
    0.06
    Activations Density 0.077%

    No Known Activations