© 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. 119354
    Prev
    Next
    INDEX
    Explanations

    statistical metrics related to 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
    ÑĢазÑĥ
    -0.07
    atile
    -0.07
    ihn
    -0.06
    ucs
    -0.06
    æĺĮ
    -0.06
     Mechan
    -0.06
    _utilities
    -0.06
    象
    -0.06
    ниÑĨе
    -0.06
    ÑĤÑĢон
    -0.06
    POSITIVE LOGITS
    advert
    0.07
    413
    0.06
     games
    0.06
     Rookie
    0.06
    //{{
    0.06
    견
    0.06
    cx
    0.06
    cro
    0.06
    acimiento
    0.05
    hlen
    0.05
    Activations Density 0.002%

    No Known Activations