© 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. 4451
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics related to sporting events

    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
    annes
    -0.07
    nika
    -0.07
    686
    -0.06
    uisine
    -0.06
    etu
    -0.06
    lue
    -0.06
    kus
    -0.06
    iene
    -0.06
    idebar
    -0.06
    uhe
    -0.06
    POSITIVE LOGITS
     Lam
    0.07
    cmc
    0.07
    Seed
    0.07
    icum
    0.07
    UD
    0.07
    æĸĻ
    0.06
     ÑħÑĢа
    0.06
     Hunt
    0.06
    ãĥ©ãĤ¹
    0.06
    urer
    0.06
    Activations Density 0.119%

    No Known Activations