© 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. 92608
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structure

    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
     Porter
    -0.06
    æŀ¶
    -0.06
    PLE
    -0.06
    ilk
    -0.06
     sp
    -0.06
     ../../../
    -0.06
    argument
    -0.06
     st
    -0.05
     ../../
    -0.05
    ette
    -0.05
    POSITIVE LOGITS
    asca
    0.08
    Âłje
    0.07
    leta
    0.07
    otland
    0.07
    chaft
    0.06
    adiens
    0.06
    lint
    0.06
    573
    0.06
     :↵↵↵↵
    0.06
     __
    0.06
    Activations Density 0.009%

    No Known Activations