© 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. 9-LLAMASCOPE-RES-131K
    11. 98220
    Prev
    Next
    INDEX
    Explanations

    special characters and comment syntax 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
    dden
    -0.07
    ahoma
    -0.07
    bris
    -0.07
    خاÙĨ
    -0.06
    aternity
    -0.06
    datable
    -0.06
    endra
    -0.06
    agle
    -0.06
    reds
    -0.06
    thon
    -0.06
    POSITIVE LOGITS
    ç¢
    0.07
    Ģ
    0.07
    رÙĪز
    0.07
    /*****************************************************************************↵
    0.07
     shl
    0.06
    ebek
    0.06
    .Abstractions
    0.06
     ÄĮech
    0.06
    scar
    0.06
    Bounds
    0.06
    Activations Density 0.001%

    No Known Activations