© 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. 104828
    Prev
    Next
    INDEX
    Explanations

    references to people and their actions or states

    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
    /loader
    -0.06
    attend
    -0.06
    acey
    -0.06
     Elephant
    -0.06
    ÙĨØ´
    -0.06
    imer
    -0.06
    ones
    -0.06
    ande
    -0.06
    ÃŃst
    -0.06
    oblin
    -0.06
    POSITIVE LOGITS
     certainly
    0.10
    pra
    0.08
    pard
    0.08
     Faul
    0.07
     also
    0.07
    istrovstvÃŃ
    0.07
    alli
    0.07
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.07
     Clarkson
    0.07
    Æ°á»Ľng
    0.07
    Activations Density 0.038%

    No Known Activations