© 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. 86377
    Prev
    Next
    INDEX
    Explanations

    terms related to health, specifically focusing on mortality and disease statistics among children and maternal health

    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
    ccione
    -0.09
    ertest
    -0.08
    orz
    -0.08
     Ñĥгод
    -0.08
    RITE
    -0.08
    caret
    -0.08
    _increment
    -0.08
    ç¾
    -0.08
     datings
    -0.07
    ournemouth
    -0.07
    POSITIVE LOGITS
     death
    0.09
     deaths
    0.09
     die
    0.08
     mortality
    0.08
    une
    0.07
     rural
    0.07
     dies
    0.06
     child
    0.06
     died
    0.06
    death
    0.06
    Activations Density 0.009%

    No Known Activations