© 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. 27553
    Prev
    Next
    INDEX
    Explanations

    references to religious persecution, particularly towards Christians and Jews

    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
    688
    -0.07
     Episcopal
    -0.06
     наÑĤ
    -0.06
    ños
    -0.06
     consumers
    -0.06
     Consumers
    -0.06
    ernals
    -0.06
    acht
    -0.06
     Cann
    -0.06
    rades
    -0.06
    POSITIVE LOGITS
     Conversion
    0.07
     conversions
    0.07
    Conversion
    0.07
     Christoph
    0.07
    lama
    0.07
     conversion
    0.07
     Sicher
    0.07
     ç¤
    0.07
    dre
    0.07
     Christians
    0.07
    Activations Density 0.008%

    No Known Activations