© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96572
    Prev
    Next
    INDEX
    Explanations

    references to different nationalities and ethnicities, particularly in the context of migration and refugee populations

    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
    ourg
    -0.07
     mue
    -0.07
    cko
    -0.07
    avid
    -0.07
    ROP
    -0.06
     Downing
    -0.06
    inine
    -0.06
    ý
    -0.06
    ault
    -0.06
    udo
    -0.06
    POSITIVE LOGITS
    Ïģθ
    0.07
     åľ
    0.07
    lund
    0.07
    .syntax
    0.07
     خبر
    0.07
    .camel
    0.07
    ÙĴÙĦ
    0.07
    Å¡ak
    0.07
    лаб
    0.07
    -scalable
    0.07
    Activations Density 0.016%

    No Known Activations