© 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. 28997
    Prev
    Next
    INDEX
    Explanations

    references to divine or spiritual figures

    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
     stuff
    -0.07
     Perez
    -0.06
    isper
    -0.06
     copy
    -0.06
     #
    -0.06
     Proud
    -0.06
     makers
    -0.06
     maker
    -0.05
     fabric
    -0.05
     mus
    -0.05
    POSITIVE LOGITS
    handleRequest
    0.07
    Bindable
    0.07
    .scalablytyped
    0.07
     CrossAxisAlignment
    0.07
    LOBAL
    0.07
     BoxFit
    0.07
    avaÅŁ
    0.07
    usercontent
    0.07
     {?>↵
    0.07
     Formal
    0.07
    Activations Density 0.001%

    No Known Activations