© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71779
    Prev
    Next
    INDEX
    Explanations

    references to racial health disparities and their impact on different communities

    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
    áºŃy
    -0.08
    dek
    -0.07
    ombat
    -0.07
    anca
    -0.07
    xFE
    -0.07
     Sanity
    -0.07
    fee
    -0.07
     ÄĮeská
    -0.06
    fleet
    -0.06
     اÙĦÙĤر
    -0.06
    POSITIVE LOGITS
     Whites
    0.07
     race
    0.07
     racial
    0.07
     White
    0.07
     distrust
    0.06
     mistr
    0.06
     races
    0.06
     whites
    0.06
    inish
    0.06
    health
    0.06
    Activations Density 0.015%

    No Known Activations