© 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 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. 29383
    Prev
    Next
    INDEX
    Explanations

    references to programming elements and libraries within code structures

    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
    acob
    -0.07
    gratis
    -0.06
    ergus
    -0.06
     Jarvis
    -0.06
    unds
    -0.06
    engan
    -0.06
    ulum
    -0.06
    .routes
    -0.06
    egt
    -0.06
    ulace
    -0.06
    POSITIVE LOGITS
    greSQL
    0.07
    atomy
    0.07
    िà¤
    0.07
    iscard
    0.07
    erras
    0.06
    onitor
    0.06
    ãĥĩãĤ£ãĤ¢
    0.06
    uten
    0.06
    anmar
    0.06
    venta
    0.06
    Activations Density 0.001%

    No Known Activations