© 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. 17-LLAMASCOPE-RES-131K
    11. 85847
    Prev
    Next
    INDEX
    Explanations

    numerical values related to sports statistics and performance

    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
    oz
    -0.07
    vider
    -0.07
    duk
    -0.07
    éf
    -0.06
    umen
    -0.06
    urt
    -0.06
    lon
    -0.06
    owell
    -0.06
    985
    -0.06
    obe
    -0.06
    POSITIVE LOGITS
     ============================================================================↵
    0.07
    à¸łà¸²à¸ŀ
    0.07
    riers
    0.07
    ÚĺÛĮ
    0.06
    ìĹħ
    0.06
    æĶ¶çĽĬ
    0.06
     à¸Ħà¸Ļ
    0.06
    ائد
    0.06
    ?action
    0.06
    à¥Īद
    0.06
    Activations Density 0.006%

    No Known Activations