© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70569
    Prev
    Next
    INDEX
    Explanations

    references to ethnic and cultural demographics

    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
    ifle
    -0.07
    adden
    -0.06
    ¼åIJĪ
    -0.06
     Omni
    -0.06
    errick
    -0.06
    anco
    -0.06
    endl
    -0.06
    ogo
    -0.06
     Kr
    -0.06
    ÑĪки
    -0.06
    POSITIVE LOGITS
     population
    0.10
     populations
    0.09
     pool
    0.08
    population
    0.08
    Population
    0.07
     Exist
    0.07
     exist
    0.07
     Marketable
    0.07
     audience
    0.07
     portion
    0.07
    Activations Density 0.057%

    No Known Activations