© 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. 95730
    Prev
    Next
    INDEX
    Explanations

    technical terms related to queries, response management, and server configurations in software

    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
    PÅĻÃŃ
    -0.08
    okud
    -0.07
     sát
    -0.07
     hại
    -0.07
     Äijiá»ĥn
    -0.06
    _Framework
    -0.06
    å¸Ń
    -0.06
    emme
    -0.06
    olley
    -0.06
    ums
    -0.06
    POSITIVE LOGITS
    Util
    0.10
     Util
    0.09
    .Util
    0.09
    Utils
    0.09
     util
    0.08
    util
    0.08
     utils
    0.08
    StringUtils
    0.07
     Utils
    0.07
    Utilities
    0.07
    Activations Density 0.052%

    No Known Activations