© 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. 125045
    Prev
    Next
    INDEX
    Explanations

    elements related to themes of mortality and dignity in the context of death

    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
    ebek
    -0.07
     Leban
    -0.07
    andest
    -0.07
    ypes
    -0.07
    zell
    -0.07
    zim
    -0.07
    isce
    -0.07
    olis
    -0.06
    lesia
    -0.06
    mere
    -0.06
    POSITIVE LOGITS
     final
    0.07
    umb
    0.07
    æľĢåIJİ
    0.06
    æľĢå¾Į
    0.06
     Execution
    0.06
    bundles
    0.06
    execution
    0.06
    FINAL
    0.06
    ogo
    0.06
     FINAL
    0.06
    Activations Density 0.002%

    No Known Activations