© 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. 95498
    Prev
    Next
    INDEX
    Explanations

    references to the Bhutanese royal family and their cultural elements

    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
     Nigerian
    -0.08
     Chicago
    -0.08
     Illinois
    -0.07
     Templ
    -0.07
     Hale
    -0.06
     Ukrainian
    -0.06
    Chicago
    -0.06
     Florida
    -0.06
     Malaysian
    -0.06
     Tampa
    -0.06
    POSITIVE LOGITS
     Vermont
    0.09
    éĽª
    0.09
     Greenland
    0.08
     Everest
    0.08
     dün
    0.08
    isoft
    0.08
    à½
    0.08
    egov
    0.07
    .bt
    0.07
     Tibetan
    0.07
    Activations Density 0.005%

    No Known Activations