© 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. 69637
    Prev
    Next
    INDEX
    Explanations

    cooking instructions related to meat preparation methods

    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
    ete
    -0.07
    /reference
    -0.06
    utzer
    -0.06
    azon
    -0.06
    ivol
    -0.06
    thinkable
    -0.06
    lac
    -0.06
    isc
    -0.06
    azen
    -0.06
    ouser
    -0.06
    POSITIVE LOGITS
    DS
    0.07
    شت
    0.07
    esh
    0.07
    ิศ
    0.07
    indy
    0.07
    رØŃ
    0.07
    ูล
    0.06
    BS
    0.06
    /goto
    0.06
    ëĬ¥
    0.06
    Activations Density 0.015%

    No Known Activations