© 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. 91928
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ular"

    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
    iç
    -0.06
    amer
    -0.06
    atan
    -0.06
    amine
    -0.06
    amation
    -0.06
    roe
    -0.06
    _LIBRARY
    -0.06
     ($("#
    -0.06
    ihu
    -0.06
    еÑģÑĮ
    -0.06
    POSITIVE LOGITS
    ized
    0.06
    abyrinth
    0.06
    loid
    0.06
    mente
    0.06
    sig
    0.06
    ffi
    0.06
    angstrom
    0.06
    ëŀĮ
    0.06
     Soci
    0.06
    ugi
    0.06
    Activations Density 0.012%

    No Known Activations