© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28459
    Prev
    Next
    INDEX
    Explanations

    references to header files in programming languages

    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
    isle
    -0.06
    ppy
    -0.06
     Visa
    -0.06
     credit
    -0.06
     Credit
    -0.06
     MatSnackBar
    -0.06
    787
    -0.06
    esti
    -0.06
    credit
    -0.06
     perc
    -0.06
    POSITIVE LOGITS
    /Foundation
    0.07
    ombat
    0.07
    INET
    0.07
     slee
    0.07
     Canary
    0.07
    aget
    0.07
    맼
    0.07
    rear
    0.07
    ãĤ´ãĥª
    0.07
    ÑĥÑĩа
    0.07
    Activations Density 0.000%

    No Known Activations