© 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. 124345
    Prev
    Next
    INDEX
    Explanations

    expressions related to overwhelming emotions or experiences

    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
    udu
    -0.07
    gency
    -0.07
    vat
    -0.07
     acomp
    -0.07
    rena
    -0.06
    inan
    -0.06
     Boeh
    -0.06
    ýv
    -0.06
    ажд
    -0.06
     trái
    -0.06
    POSITIVE LOGITS
     handle
    0.07
    brick
    0.07
    ehr
    0.07
     Handle
    0.07
    uman
    0.06
    handle
    0.06
     handled
    0.06
     load
    0.06
     Sext
    0.06
    manage
    0.06
    Activations Density 0.033%

    No Known Activations