© 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. 15-LLAMASCOPE-RES-131K
    11. 86381
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their rankings

    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
    odus
    -0.07
    sert
    -0.07
    ÙĪجÙĩ
    -0.07
    á»IJ
    -0.07
    Ñĩна
    -0.07
    Namespace
    -0.07
    Ñıд
    -0.07
    ahan
    -0.07
    .btnExit
    -0.07
     průbÄĽhu
    -0.07
    POSITIVE LOGITS
    anian
    0.06
     Edmund
    0.06
     gim
    0.06
     Ast
    0.06
    erras
    0.06
    emand
    0.06
     Sad
    0.06
     Bid
    0.05
     followed
    0.05
     Bel
    0.05
    Activations Density 0.023%

    No Known Activations