© 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. 30491
    Prev
    Next
    INDEX
    Explanations

    references to swimming competitions and team 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
     ground
    -0.08
     rolling
    -0.07
    rolling
    -0.07
    è¿ŀ
    -0.07
    anguage
    -0.06
    çİ©
    -0.06
    太éĥİ
    -0.06
    _ground
    -0.06
    çIJĥ
    -0.06
     softball
    -0.06
    POSITIVE LOGITS
     swim
    0.15
     swimming
    0.14
     Swimming
    0.14
     Swim
    0.14
     swims
    0.12
    æ³³
    0.12
     pisc
    0.10
     aquatic
    0.10
     aqu
    0.10
     Aqu
    0.10
    Activations Density 0.043%

    No Known Activations