© 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. 73852
    Prev
    Next
    INDEX
    Explanations

    references to Jesus Christ and his divine attributes

    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
    trak
    -0.07
    lect
    -0.06
     land
    -0.06
    lust
    -0.06
    909
    -0.06
     Concord
    -0.06
     opportunity
    -0.06
    vore
    -0.06
    641
    -0.06
    rych
    -0.06
    POSITIVE LOGITS
     Nimbus
    0.08
    -navbar
    0.08
    azzo
    0.07
     birth
    0.07
     taj
    0.07
    strcasecmp
    0.07
    _birth
    0.07
    manuel
    0.06
    ải
    0.06
    .psi
    0.06
    Activations Density 0.020%

    No Known Activations