© 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. 15-LLAMASCOPE-RES-131K
    11. 87552
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their derivatives

    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
    oz
    -0.06
    ibur
    -0.06
    lj
    -0.06
    ivery
    -0.06
    ont
    -0.06
    leigh
    -0.06
    erglass
    -0.06
    datatable
    -0.06
    ../../../../
    -0.05
    otland
    -0.05
    POSITIVE LOGITS
    edom
    0.07
     Lup
    0.07
     production
    0.07
    ');?>↵
    0.07
     productions
    0.07
    /raw
    0.07
    ÅĻÃŃm
    0.07
     produced
    0.07
     Flo
    0.07
    ابت
    0.07
    Activations Density 0.016%

    No Known Activations