© 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. 17-LLAMASCOPE-RES-131K
    11. 3612
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual concepts, particularly focusing on the idea of the Antichrist

    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
    assage
    -0.07
    anax
    -0.07
    風
    -0.07
    üml
    -0.07
    VRT
    -0.07
    upe
    -0.07
     ÙĥÙĨد
    -0.07
    762
    -0.07
    onde
    -0.07
     safeg
    -0.07
    POSITIVE LOGITS
     Revel
    0.07
     Ant
    0.07
     rider
    0.06
     revel
    0.06
     riding
    0.06
     cam
    0.06
    0.06
     ant
    0.06
    eden
    0.06
     purpose
    0.06
    Activations Density 0.009%

    No Known Activations