© 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. 2247
    Prev
    Next
    INDEX
    Explanations

    references to fitness routines and workout exercises

    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
     tal
    -0.07
    steen
    -0.07
    iage
    -0.06
    nel
    -0.06
    craft
    -0.06
    apon
    -0.06
     Beard
    -0.06
     Stam
    -0.06
    Marks
    -0.06
    :@""
    -0.06
    POSITIVE LOGITS
     fitness
    0.12
     training
    0.12
     trainer
    0.11
     Training
    0.10
     gym
    0.10
     workouts
    0.10
     workout
    0.10
     Trainer
    0.10
     Fitness
    0.10
    Training
    0.10
    Activations Density 0.128%

    No Known Activations