© 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. 62912
    Prev
    Next
    INDEX
    Explanations

    terms related to sports leagues and professional 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
    ovit
    -0.07
    pmat
    -0.07
    unction
    -0.07
     Gil
    -0.07
    ожеÑĤ
    -0.06
    lesia
    -0.06
    ctp
    -0.06
    reff
    -0.06
    ê¶Į
    -0.06
    archy
    -0.06
    POSITIVE LOGITS
    answered
    0.07
    GS
    0.06
     appearances
    0.06
    uge
    0.06
     appearance
    0.06
    ugh
    0.06
    QE
    0.06
    ova
    0.06
    ang
    0.06
    yas
    0.06
    Activations Density 0.012%

    No Known Activations