© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53902
    Prev
    Next
    INDEX
    Explanations

    references to honoring and celebrating lives, particularly in the context of memorials or funerals

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    sburg
    -0.07
     htonl
    -0.07
    owie
    -0.07
     ÄĮer
    -0.07
    ople
    -0.07
     Pell
    -0.07
    翼
    -0.07
    ",__
    -0.07
    uras
    -0.07
    isti
    -0.06
    POSITIVE LOGITS
     life
    0.11
     lives
    0.09
     Life
    0.08
     życ
    0.08
    life
    0.08
    -life
    0.08
     Leben
    0.08
    Life
    0.08
     LIFE
    0.07
     vida
    0.07
    Activations Density 0.003%

    No Known Activations