© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108940
    Prev
    Next
    INDEX
    Explanations

    references to divine creation and the concept of being made in God's image

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    erland
    -0.09
    igin
    -0.07
    ırak
    -0.07
    erse
    -0.06
     Neutral
    -0.06
     Hood
    -0.06
    aktion
    -0.06
    ENUM
    -0.06
    idar
    -0.06
     discreet
    -0.06
    POSITIVE LOGITS
     likeness
    0.11
    Lon
    0.07
     Facilities
    0.07
     resembl
    0.07
    hausen
    0.07
     Lon
    0.07
     resemblance
    0.07
    formation
    0.07
    äm
    0.06
    ertz
    0.06
    Activations Density 0.015%

    No Known Activations