© 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 EvalsExportsAPI 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. 29024
    Prev
    Next
    INDEX
    Explanations

    terms associated with physical activity and improvement

    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
    کز
    -0.06
    anger
    -0.06
    izar
    -0.06
    wish
    -0.06
    starter
    -0.06
     manic
    -0.06
     flutter
    -0.06
    Å¡ov
    -0.06
    éĩı
    -0.06
    ieux
    -0.06
    POSITIVE LOGITS
    ernaut
    0.08
     locom
    0.07
     forControlEvents
    0.07
    .mob
    0.07
    -functional
    0.07
     functional
    0.07
    .selectAll
    0.06
    adaÅŁ
    0.06
     athleticism
    0.06
     body
    0.06
    Activations Density 0.001%

    No Known Activations