© 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. 128795
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to measurements

    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
    enia
    -0.07
     Programm
    -0.06
     programm
    -0.06
    posted
    -0.06
    imson
    -0.06
    enie
    -0.06
    ylon
    -0.06
    fty
    -0.06
    縮
    -0.06
    atrix
    -0.06
    POSITIVE LOGITS
     Hou
    0.07
    輪
    0.07
    ousel
    0.06
    ÛĮرÛĮ
    0.06
    _instructions
    0.06
    ÌĢ
    0.06
    .componentInstance
    0.06
    .Dimension
    0.06
    :id
    0.06
    Instructions
    0.06
    Activations Density 0.088%

    No Known Activations