© 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. 9-LLAMASCOPE-RES-131K
    11. 97447
    Prev
    Next
    INDEX
    Explanations

    phrases related to the scoring and performance in sports

    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
     Emanuel
    -0.07
    keley
    -0.07
    ouv
    -0.07
    ailles
    -0.07
    olo
    -0.07
    иÑĤоÑĢ
    -0.06
    ÑĢозÑĥм
    -0.06
    uard
    -0.06
    ýš
    -0.06
    ispens
    -0.06
    POSITIVE LOGITS
    Ú¯ÛĮ
    0.06
     dot
    0.06
    vie
    0.06
    ovat
    0.06
    æĸ°èģŀ
    0.06
    Ìģ
    0.06
    ighton
    0.06
    fern
    0.05
    ToOne
    0.05
    angu
    0.05
    Activations Density 0.006%

    No Known Activations