© 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. 41474
    Prev
    Next
    INDEX
    Explanations

    references to acknowledging or signaling understanding through nods

    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
    arian
    -0.08
    arians
    -0.08
    wolf
    -0.07
    ouser
    -0.07
    outh
    -0.07
    wap
    -0.07
    abad
    -0.07
    EndElement
    -0.07
    furt
    -0.07
    @synthesize
    -0.07
    POSITIVE LOGITS
    ding
    0.07
    afür
    0.07
    ularity
    0.07
    ging
    0.07
    cker
    0.06
    ting
    0.06
     gesture
    0.06
    yssey
    0.06
     toward
    0.06
    ÂŁ
    0.06
    Activations Density 0.003%

    No Known Activations