© 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. 62120
    Prev
    Next
    INDEX
    Explanations

    actions and gestures related to pointing or directing attention

    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
    _DEPRECATED
    -0.08
    /inet
    -0.07
     Telephone
    -0.07
    ummer
    -0.07
    inka
    -0.06
     franca
    -0.06
    ync
    -0.06
    dam
    -0.06
    eco
    -0.06
    ycop
    -0.06
    POSITIVE LOGITS
     Wand
    0.06
    ÏĦοÏį
    0.06
     wand
    0.06
    oland
    0.06
    lesen
    0.06
    ches
    0.06
    bew
    0.06
    loyd
    0.06
    aris
    0.06
     gest
    0.06
    Activations Density 0.012%

    No Known Activations