© 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. 98043
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gary" and its variants in various contexts

    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
    ese
    -0.09
    اتÛĮ
    -0.08
    åħ·
    -0.07
    lore
    -0.07
    osal
    -0.07
    arehouse
    -0.07
    pper
    -0.07
    elder
    -0.07
    mür
    -0.07
    /embed
    -0.06
    POSITIVE LOGITS
    ullo
    0.07
    sburg
    0.07
    dır
    0.07
    arus
    0.07
    amac
    0.07
    fly
    0.07
    aran
    0.07
    бÑĥÑĤ
    0.07
    EIF
    0.07
    nt
    0.06
    Activations Density 0.042%

    No Known Activations