© 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. 41411
    Prev
    Next
    INDEX
    Explanations

    instances of physical affection or supportive gestures between individuals

    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
    yard
    -0.07
    olutely
    -0.07
    ebi
    -0.07
    eneg
    -0.07
    presso
    -0.07
    enou
    -0.07
    ispens
    -0.07
    опиÑģ
    -0.07
    ytt
    -0.07
    .opend
    -0.07
    POSITIVE LOGITS
     pat
    0.09
    pat
    0.06
     approaches
    0.06
     taps
    0.06
     approach
    0.06
    438
    0.06
     hand
    0.06
    (pat
    0.06
     fine
    0.06
     comm
    0.05
    Activations Density 0.010%

    No Known Activations