© 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. 95837
    Prev
    Next
    INDEX
    Explanations

    data and numerical values related to physical measurements or scientific calculations

    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
    лен
    -0.06
    %</
    -0.06
     ↵↵
    -0.06
    igi
    -0.06
    wen
    -0.06
    lime
    -0.06
    athan
    -0.06
     feas
    -0.06
     Horton
    -0.06
     Maz
    -0.06
    POSITIVE LOGITS
    alytics
    0.07
    mgr
    0.07
    missive
    0.06
     vois
    0.06
    assel
    0.06
    ingers
    0.06
    borg
    0.06
     AssemblyVersion
    0.06
    zek
    0.06
    Dup
    0.06
    Activations Density 0.156%

    No Known Activations