© 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. 88507
    Prev
    Next
    INDEX
    Explanations

    actions involving physical interactions and manipulations

    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
    \grid
    -0.07
    bÃŃ
    -0.07
     Phòng
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    .jasper
    -0.07
    .sd
    -0.07
    溶
    -0.07
    akan
    -0.07
    uluk
    -0.07
    avery
    -0.07
    POSITIVE LOGITS
     handle
    0.09
     handles
    0.09
     Grab
    0.08
     grab
    0.08
    hold
    0.08
     handful
    0.07
     hold
    0.07
    handle
    0.07
    -handle
    0.07
    grab
    0.07
    Activations Density 0.046%

    No Known Activations