© 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 EvalsExportsAPI 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. 86092
    Prev
    Next
    INDEX
    Explanations

    procedures and steps related to baking and cooking

    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
     glob
    -0.07
    ayi
    -0.06
    glob
    -0.06
    utow
    -0.06
    ilst
    -0.06
     Tank
    -0.06
     Bea
    -0.06
     tanks
    -0.06
    /preferences
    -0.06
    ripp
    -0.06
    POSITIVE LOGITS
    olland
    0.07
     baking
    0.07
    dummy
    0.07
     dummy
    0.07
    MethodImpl
    0.06
    stice
    0.06
    oven
    0.06
    InterfaceOrientation
    0.06
    adi
    0.06
    rap
    0.06
    Activations Density 0.018%

    No Known Activations