© 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. 9-LLAMASCOPE-RES-131K
    11. 97046
    Prev
    Next
    INDEX
    Explanations

    references to university sports conferences and teams

    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
    ourt
    -0.07
    imes
    -0.07
    our
    -0.06
    hek
    -0.06
    zi
    -0.06
    stan
    -0.06
     Julien
    -0.06
     Ting
    -0.06
    owy
    -0.06
    sta
    -0.06
    POSITIVE LOGITS
    HITE
    0.07
    illard
    0.07
    StateChanged
    0.07
    erties
    0.07
    erte
    0.07
    .paper
    0.07
    isu
    0.07
    SEG
    0.06
     nonlinear
    0.06
    å«
    0.06
    Activations Density 0.003%

    No Known Activations