© 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. 120210
    Prev
    Next
    INDEX
    Explanations

    references to football (soccer) matches and competitions

    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
     mah
    -0.07
     lap
    -0.06
     Mah
    -0.06
    IMIT
    -0.06
    лÑĸд
    -0.06
    agma
    -0.06
    ẩm
    -0.06
    elop
    -0.06
    idth
    -0.06
     stamps
    -0.06
    POSITIVE LOGITS
     Rad
    0.07
     Lives
    0.07
     entry
    0.06
    æĬ½
    0.06
    sted
    0.06
     holders
    0.06
     cup
    0.06
    Rad
    0.06
    CALE
    0.06
     Entry
    0.06
    Activations Density 0.007%

    No Known Activations