© 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. 121111
    Prev
    Next
    INDEX
    Explanations

    references to divine presence and protection

    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
     Cumhur
    -0.08
    unks
    -0.07
    meli
    -0.07
     blat
    -0.07
     fisse
    -0.07
    acro
    -0.07
     valign
    -0.07
    ÄĽle
    -0.06
    reon
    -0.06
    ximity
    -0.06
    POSITIVE LOGITS
    oga
    0.06
     carbon
    0.06
    pe
    0.06
    tek
    0.06
    ZW
    0.06
     g
    0.06
    ai
    0.06
     double
    0.06
    è¨
    0.06
     stag
    0.06
    Activations Density 0.005%

    No Known Activations