© 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. 18084
    Prev
    Next
    INDEX
    Explanations

    references to humorous content and quotations

    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
    .libs
    -0.07
    trak
    -0.07
    erken
    -0.07
    emark
    -0.07
    íĥĢìĿ´
    -0.06
     fakt
    -0.06
    amping
    -0.06
    adder
    -0.06
    DAQ
    -0.06
    ÑĤÑĢ
    -0.06
    POSITIVE LOGITS
    ernels
    0.06
    enance
    0.06
    asury
    0.06
    .OrderByDescending
    0.06
     eÅŁ
    0.06
    ipel
    0.06
    axies
    0.06
    XD
    0.06
    net
    0.06
    ogn
    0.06
    Activations Density 0.004%

    No Known Activations