© 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. 92081
    Prev
    Next
    INDEX
    Explanations

    references to people, specifically names associated with images or articles

    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
     Esp
    -0.06
    -0.06
     Merk
    -0.06
     armed
    -0.06
    anvas
    -0.06
     Graz
    -0.06
     Horn
    -0.06
    주ìĭľ
    -0.06
     mer
    -0.06
     esp
    -0.06
    POSITIVE LOGITS
    argout
    0.08
    Enlarge
    0.08
    swire
    0.07
    itchens
    0.07
    -wsj
    0.07
    latlong
    0.07
     eventdata
    0.07
    istrovstvÃŃ
    0.07
     fetisch
    0.07
    ccak
    0.07
    Activations Density 0.031%

    No Known Activations