© 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. 54868
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to creating and managing items or variables in code

    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
    esub
    -0.07
    Outlined
    -0.06
    PointerType
    -0.06
    á»ķ
    -0.06
    achs
    -0.06
    //{{
    -0.06
    ozo
    -0.06
    Thrown
    -0.06
    Occurred
    -0.06
    Backing
    -0.06
    POSITIVE LOGITS
    ():↵
    0.07
    <TResult
    0.07
    ():
    0.07
    (){↵
    0.07
     latter
    0.06
    mage
    0.06
     ():
    0.06
    áz
    0.06
    ()
    0.06
    /create
    0.06
    Activations Density 0.039%

    No Known Activations