© 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. 41329
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional reactions or judgments

    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
     çı
    -0.06
    into
    -0.06
    elry
    -0.06
    quare
    -0.06
    zon
    -0.06
    ining
    -0.06
    [sizeof
    -0.06
    elage
    -0.06
    มา
    -0.06
    entai
    -0.06
    POSITIVE LOGITS
     Cooler
    0.07
     Cool
    0.07
    Cool
    0.07
     Summon
    0.06
     coolest
    0.06
     cool
    0.06
    骨
    0.06
     cooler
    0.06
    cool
    0.06
    ıt
    0.06
    Activations Density 0.006%

    No Known Activations