© 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 EvalsExportsAPI 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. 78345
    Prev
    Next
    INDEX
    Explanations

    the word "but" and its variations to highlight contrasting ideas or exceptions

    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
    eniz
    -0.07
     Kaynak
    -0.07
     kıl
    -0.07
    åĽ
    -0.07
     åĨĨ
    -0.07
     lại
    -0.07
    enaire
    -0.07
    Ìģt
    -0.07
    oti
    -0.07
    .dump
    -0.07
    POSITIVE LOGITS
     otherwise
    0.08
    Anyway
    0.08
     nevertheless
    0.07
     Anyway
    0.07
     still
    0.07
     basically
    0.07
     Still
    0.07
     fine
    0.07
     nonetheless
    0.06
     Otherwise
    0.06
    Activations Density 0.037%

    No Known Activations