© 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. 124466
    Prev
    Next
    INDEX
    Explanations

    references to spiritual or religious practices and the importance of scripture in personal lives

    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
    neck
    -0.07
     Pier
    -0.07
    etta
    -0.06
     unb
    -0.06
    loor
    -0.06
    erve
    -0.06
     Starter
    -0.06
    avec
    -0.06
     Gerr
    -0.06
     Sever
    -0.05
    POSITIVE LOGITS
     Ownership
    0.09
     ownership
    0.08
    ownership
    0.08
    Ownership
    0.07
     permanent
    0.07
     assim
    0.07
    Permanent
    0.07
    OWNER
    0.07
     INTERNAL
    0.07
    eon
    0.07
    Activations Density 0.037%

    No Known Activations