© 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. 117434
    Prev
    Next
    INDEX
    Explanations

    file types and navigation elements in digital contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML/web interface elements like arrows, icons, buttons, and navigation controls often marked with underscores or descriptive tags indicating their function or appearance in code.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    .cgi
    -0.07
    nable
    -0.06
    åĿĤ
    -0.06
    ÙĦÙī
    -0.06
    гл
    -0.06
     Burl
    -0.06
    มà¸Ń
    -0.06
    æİĴ
    -0.06
    oub
    -0.06
    okus
    -0.06
    POSITIVE LOGITS
    chwitz
    0.07
    standen
    0.07
    æŀª
    0.06
    ï¸
    0.06
    vero
    0.06
    ulton
    0.06
    -symbol
    0.06
     Rein
    0.06
    leton
    0.06
    /Users
    0.06
    Activations Density 0.016%

    No Known Activations