© 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. 4902
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure in programming contexts

    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
    ئت
    -0.08
    опол
    -0.08
    uteur
    -0.07
    edla
    -0.07
     volta
    -0.07
    readcr
    -0.07
     пÑĢив
    -0.07
    dbContext
    -0.07
    CursorPosition
    -0.06
    ocator
    -0.06
    POSITIVE LOGITS
    .html
    0.07
    ault
    0.06
    isch
    0.06
    .gif
    0.06
    fold
    0.06
    yx
    0.06
    axon
    0.06
     Andersen
    0.05
    ados
    0.05
    undos
    0.05
    Activations Density 0.000%

    No Known Activations