© 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. 14576
    Prev
    Next
    INDEX
    Explanations

    references to physical fitness and exercise 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
    βι
    -0.07
    steen
    -0.07
    vit
    -0.07
    æķ·
    -0.07
     Foreign
    -0.06
    ulent
    -0.06
    tem
    -0.06
    ertino
    -0.06
    alem
    -0.06
    steam
    -0.06
    POSITIVE LOGITS
     upper
    0.07
     muscles
    0.07
     solic
    0.07
     erect
    0.07
    inea
    0.06
     sp
    0.06
    imi
    0.06
     bust
    0.06
    upper
    0.06
     demand
    0.06
    Activations Density 0.004%

    No Known Activations