© 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. 93355
    Prev
    Next
    INDEX
    Explanations

    references to religious doctrines and significant theological concepts

    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
    abee
    -0.07
    quate
    -0.07
    -disabled
    -0.06
    fty
    -0.06
    antro
    -0.06
    abi
    -0.06
    ëħķ
    -0.06
    olis
    -0.06
    atomic
    -0.06
    icode
    -0.06
    POSITIVE LOGITS
    å¡ļ
    0.07
    ̣
    0.07
    loser
    0.07
    .nano
    0.06
    æĬľ
    0.06
    å¥Ī
    0.06
    enet
    0.06
    رÛĮاÙĨ
    0.06
     bund
    0.06
     latter
    0.06
    Activations Density 0.224%

    No Known Activations