© 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. 129837
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationship with religious institutions and communities

    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
     citt
    -0.07
    bot
    -0.06
     èĦ
    -0.06
     Mund
    -0.06
    iss
    -0.06
    >manual
    -0.06
    å²
    -0.06
    ries
    -0.06
    cket
    -0.05
     shared
    -0.05
    POSITIVE LOGITS
     traditional
    0.08
     regular
    0.07
    isÃŃ
    0.07
    iform
    0.07
    unday
    0.07
     stigma
    0.07
    asics
    0.07
     Regular
    0.07
    regular
    0.07
    Regular
    0.07
    Activations Density 0.019%

    No Known Activations