© 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. 105101
    Prev
    Next
    INDEX
    Explanations

    discussions and descriptions of concepts, particularly in the context of art, philosophy, and social issues

    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
    Äįer
    -0.07
    á»ĵn
    -0.07
    /respond
    -0.07
    eton
    -0.06
    andre
    -0.06
    uja
    -0.06
     näch
    -0.06
    ei
    -0.06
    plode
    -0.06
     current
    -0.06
    POSITIVE LOGITS
     famously
    0.07
     createState
    0.07
    bury
    0.07
    ificio
    0.06
     PMID
    0.06
    827
    0.06
    DMI
    0.06
     similarly
    0.06
    rador
    0.06
    766
    0.06
    Activations Density 0.066%

    No Known Activations