© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128466
    Prev
    Next
    INDEX
    Explanations

    references to the Prophet Muhammad and his significance in Islamic teachings

    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
    ijo
    -0.06
    abar
    -0.06
    ieux
    -0.06
    sen
    -0.06
     Granite
    -0.06
    anj
    -0.06
    amo
    -0.06
    splash
    -0.06
    isable
    -0.06
    atta
    -0.06
    POSITIVE LOGITS
     صÙĦÙī
    0.08
    (pb
    0.08
    iena
    0.07
    laÄį
    0.07
    664
    0.07
    زÛĮ
    0.07
    bane
    0.07
    ãģıãĤī
    0.07
    reich
    0.07
    essim
    0.07
    Activations Density 0.007%

    No Known Activations