© 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. 30012
    Prev
    Next
    INDEX
    Explanations

    terms related to Chinese concepts of health and energy balance

    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
     worth
    -0.06
    yd
    -0.06
    azine
    -0.06
    doll
    -0.06
     requ
    -0.06
    edn
    -0.06
    ìĭ¬
    -0.05
     reject
    -0.05
     Stake
    -0.05
    zier
    -0.05
    POSITIVE LOGITS
     gridColumn
    0.07
     Principle
    0.07
    usta
    0.07
    çĤ®
    0.07
    /Gate
    0.07
    ÑĢик
    0.07
    #__
    0.07
    plx
    0.07
     Ay
    0.07
    ạng
    0.07
    Activations Density 0.006%

    No Known Activations