© 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. 86079
    Prev
    Next
    INDEX
    Explanations

    statistics and performance measures in sports contexts

    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
    ivet
    -0.07
     minul
    -0.07
    afort
    -0.07
    argar
    -0.07
    ertino
    -0.07
    YPD
    -0.07
    rego
    -0.06
    à¥įदर
    -0.06
    ัà¸įà¸į
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
     "
    0.07
    137
    0.06
     Ging
    0.06
    ijo
    0.06
    0.06
     altern
    0.06
    wan
    0.06
     inter
    0.05
     era
    0.05
     Abram
    0.05
    Activations Density 0.001%

    No Known Activations