© 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. 54608
    Prev
    Next
    INDEX
    Explanations

    references to "Gatton" in various contexts, likely related to a specific college or institution

    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
    ãĥ¼ãĥIJ
    -0.07
    ateful
    -0.07
     cô
    -0.07
    ourd
    -0.06
    ÎŃν
    -0.06
    anche
    -0.06
    reachable
    -0.06
    auen
    -0.06
    eph
    -0.06
    uli
    -0.06
    POSITIVE LOGITS
    воÑĢ
    0.07
    ston
    0.06
    wald
    0.06
     maur
    0.06
    озем
    0.06
    /portfolio
    0.06
    bred
    0.06
    wal
    0.06
     yat
    0.06
    oland
    0.06
    Activations Density 0.013%

    No Known Activations