© 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. 104389
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols used in mathematical equations

    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
    inheritDoc
    -0.07
    ouncements
    -0.07
    luent
    -0.07
    andr
    -0.07
    ÑģпÑĸлÑĮ
    -0.06
    大ä¼ļ
    -0.06
     multis
    -0.06
    ramento
    -0.06
    .epsilon
    -0.06
    traits
    -0.06
    POSITIVE LOGITS
    anus
    0.07
    Ģë¡ľ
    0.06
    oro
    0.06
    CEL
    0.06
    uka
    0.06
    deb
    0.06
    ottie
    0.06
    vos
    0.06
    etto
    0.05
    举
    0.05
    Activations Density 0.068%

    No Known Activations