© 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. 9-LLAMASCOPE-RES-131K
    11. 98767
    Prev
    Next
    INDEX
    Explanations

    variations of the word "roll."

    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
    uthor
    -0.08
    zelf
    -0.07
    imals
    -0.07
    /how
    -0.07
    bsolute
    -0.07
    ogo
    -0.07
    others
    -0.07
    -être
    -0.07
    .UnitTesting
    -0.07
    elmet
    -0.07
    POSITIVE LOGITS
    ìį¨
    0.08
    ero
    0.08
    beck
    0.08
    heck
    0.07
    ábado
    0.07
    ç¨ĭ
    0.07
    -ÑĤаки
    0.07
    anks
    0.07
    otta
    0.07
    &type
    0.07
    Activations Density 0.024%

    No Known Activations