© 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. 79425
    Prev
    Next
    INDEX
    Explanations

    references to bodily health and physiological conditions

    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
    átka
    -0.08
    iry
    -0.07
    orce
    -0.07
    ekt
    -0.07
    egal
    -0.07
    anna
    -0.07
    /documentation
    -0.07
    uling
    -0.07
    gal
    -0.07
    çħ
    -0.07
    POSITIVE LOGITS
     mechanisms
    0.08
     processes
    0.07
     mechanism
    0.07
    /System
    0.06
    926
    0.06
    531
    0.06
     itself
    0.06
    -US
    0.06
    826
    0.06
     Burr
    0.06
    Activations Density 0.013%

    No Known Activations