© 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. 30167
    Prev
    Next
    INDEX
    Explanations

    contextual references to sports performance and potential outcomes

    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
    ãģ°ãģĭãĤĬ
    -0.07
    REFERRED
    -0.07
    .latest
    -0.07
    以æĿ¥
    -0.07
     discrepan
    -0.07
     lately
    -0.07
     nors
    -0.07
    æĿī
    -0.07
    /parser
    -0.06
    thora
    -0.06
    POSITIVE LOGITS
     Year
    0.07
     somewhere
    0.06
    ä»Ĭå¹´
    0.06
    lech
    0.06
     Mig
    0.06
    ocoder
    0.06
    igli
    0.06
    Scheme
    0.06
    kehr
    0.06
    wang
    0.06
    Activations Density 0.068%

    No Known Activations