© 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. 120460
    Prev
    Next
    INDEX
    Explanations

    fragments of programming code and associated syntax

    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
    unsch
    -0.07
    primir
    -0.07
    lero
    -0.07
    leri
    -0.07
    tring
    -0.06
    acct
    -0.06
    úsqueda
    -0.06
    abay
    -0.06
    duct
    -0.06
    ÙĨØ´
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.07
    _sun
    0.06
    baugh
    0.06
    âĨĵ
    0.06
    371
    0.06
    851
    0.06
    iswa
    0.06
     ÐľÐ¸ÐºÐ¾Ð»Ð°
    0.06
    ios
    0.06
    0.06
    Activations Density 0.010%

    No Known Activations