© 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. 92310
    Prev
    Next
    INDEX
    Explanations

    references to regulatory entities and compliance metrics

    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
     Beg
    -0.06
    rette
    -0.06
     Polic
    -0.06
    ег
    -0.06
     Orr
    -0.06
     Todd
    -0.05
    inkel
    -0.05
    euillez
    -0.05
    kus
    -0.05
    ording
    -0.05
    POSITIVE LOGITS
    vÃŃ
    0.07
    _utilities
    0.07
    agna
    0.07
    ãĥªãĤ«
    0.06
    gree
    0.06
    -translate
    0.06
    /UIKit
    0.06
    emode
    0.06
     actually
    0.06
    untu
    0.06
    Activations Density 0.023%

    No Known Activations