© 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. 54583
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS structural elements, particularly related to divs and classes used in a web layout

    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
    typeorm
    -0.06
    icates
    -0.06
    hog
    -0.06
     fre
    -0.06
    ngle
    -0.06
     Hog
    -0.06
    _->
    -0.06
     vis
    -0.06
    mdb
    -0.05
    ALSE
    -0.05
    POSITIVE LOGITS
    öyle
    0.07
    ONENT
    0.07
    atura
    0.06
     main
    0.06
    UNUSED
    0.06
    main
    0.06
    iggins
    0.06
     clearfix
    0.06
    /details
    0.06
    overall
    0.06
    Activations Density 0.019%

    No Known Activations