© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59698
    Prev
    Next
    INDEX
    Explanations

    programming-related concepts and constructs

    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
    cela
    -0.07
    cestor
    -0.07
    ritch
    -0.07
    unce
    -0.07
    lez
    -0.07
    phia
    -0.07
    ysi
    -0.07
    amment
    -0.07
    _soft
    -0.06
    _flutter
    -0.06
    POSITIVE LOGITS
    .Collectors
    0.09
    s
    0.07
     damp
    0.06
    ener
    0.06
    Ïģιν
    0.06
    nÃŃ
    0.06
     folds
    0.06
     fold
    0.06
     Prior
    0.06
    æĿ¿
    0.06
    Activations Density 0.000%

    No Known Activations