© 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. 38980
    Prev
    Next
    INDEX
    Explanations

    symbols and variables typically used in mathematical equations or scientific formulas

    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
    illet
    -0.07
    apan
    -0.07
    olan
    -0.07
    chez
    -0.07
    ãģıãĤĮ
    -0.07
    лагод
    -0.07
    ooke
    -0.07
    omu
    -0.07
    obre
    -0.07
    WK
    -0.07
    POSITIVE LOGITS
    âijł
    0.07
    .annotations
    0.07
     qua
    0.06
    led
    0.06
    ãĢĩ
    0.06
    sett
    0.05
    iyim
    0.05
    istr
    0.05
     Casc
    0.05
    auc
    0.05
    Activations Density 0.093%

    No Known Activations