© 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. 17723
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to functions and methods

    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
     |--------------------------------------------------------------------------↵
    -0.07
     åħ±
    -0.07
    arat
    -0.07
    /*č↵
    -0.07
    arih
    -0.07
    çĭIJ
    -0.07
    çĻ
    -0.07
    าà¸Īาà¸ģ
    -0.06
     nebu
    -0.06
    alon
    -0.06
    POSITIVE LOGITS
     main
    0.08
     meth
    0.07
    meth
    0.06
    idebar
    0.06
     GU
    0.06
     Main
    0.06
    /main
    0.06
     ConfigureServices
    0.06
    methodName
    0.06
     METH
    0.05
    Activations Density 0.033%

    No Known Activations