© 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. 73345
    Prev
    Next
    INDEX
    Explanations

    terms related to sports and physical activities

    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
    ignet
    -0.07
    xfff
    -0.07
    ugas
    -0.07
    vou
    -0.07
    apl
    -0.07
    åıĬåħ¶
    -0.07
    åĮħæĭ¬
    -0.06
    een
    -0.06
    umes
    -0.06
    ãģĵãģĿ
    -0.06
    POSITIVE LOGITS
     etc
    0.11
    etc
    0.09
     ones
    0.07
     or
    0.07
     others
    0.07
    ãģªãģ©
    0.07
     czy
    0.07
     коÑĤоÑĢÑĭÑħ
    0.07
     which
    0.07
    Untitled
    0.07
    Activations Density 0.110%

    No Known Activations