© 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. 106493
    Prev
    Next
    INDEX
    Explanations

    references to theological concepts and significant figures in religious discourse

    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
    /xhtml
    -0.07
    'y
    -0.06
    æ¤į
    -0.06
    ofilm
    -0.06
    ampie
    -0.06
    inka
    -0.06
    kuk
    -0.06
    ’y
    -0.06
     Quiz
    -0.06
     value
    -0.06
    POSITIVE LOGITS
    anes
    0.07
    ойно
    0.07
     Souls
    0.07
     Hil
    0.06
     al
    0.06
     Sight
    0.06
     Tay
    0.06
     McGregor
    0.06
     sadd
    0.06
     Ocean
    0.06
    Activations Density 0.026%

    No Known Activations