© 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. 124762
    Prev
    Next
    INDEX
    Explanations

    references to physical exercise and strength training

    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
     Bucket
    -0.06
     bucket
    -0.06
    kin
    -0.06
    ilon
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
     cat
    -0.06
    odel
    -0.05
    кÑĸн
    -0.05
     Macy
    -0.05
     chatte
    -0.05
    POSITIVE LOGITS
     gradually
    0.07
     Ñĥвели
    0.07
    ptest
    0.07
     postupnÄĽ
    0.07
    incre
    0.07
     ability
    0.07
    unta
    0.07
    -collapse
    0.07
    PEG
    0.07
     gradual
    0.07
    Activations Density 0.009%

    No Known Activations