© 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. 15-LLAMASCOPE-RES-131K
    11. 86790
    Prev
    Next
    INDEX
    Explanations

    incidents involving elevation changes or dangerous drops

    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
     Extra
    -0.07
     extra
    -0.07
    ymax
    -0.06
    extra
    -0.06
    uli
    -0.06
    ucceeded
    -0.06
     tor
    -0.05
    rien
    -0.05
     sparing
    -0.05
     underwater
    -0.05
    POSITIVE LOGITS
    MMC
    0.08
    morgan
    0.08
     nackte
    0.07
    scriptId
    0.07
     dziew
    0.07
     Mundo
    0.07
    repid
    0.07
    .imag
    0.07
    buie
    0.07
     smrti
    0.07
    Activations Density 0.017%

    No Known Activations