© 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. 81657
    Prev
    Next
    INDEX
    Explanations

    themes of tragedy and tragic events

    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
    à¸Ļะ
    -0.07
    ÑĢив
    -0.07
    iw
    -0.07
     grosse
    -0.07
    strategy
    -0.07
    ikan
    -0.07
    isations
    -0.07
    i
    -0.06
    ieg
    -0.06
    iage
    -0.06
    POSITIVE LOGITS
    omic
    0.11
    omik
    0.08
    hetto
    0.07
    ÚĨÙĩ
    0.07
     Clo
    0.07
    omas
    0.07
    -com
    0.06
    amespace
    0.06
    kest
    0.06
    omed
    0.06
    Activations Density 0.006%

    No Known Activations