© 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. 128344
    Prev
    Next
    INDEX
    Explanations

    themes related to the intersection of religion and culture

    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
    sei
    -0.08
     Jehovah
    -0.08
    .gdx
    -0.08
    SGlobal
    -0.08
    acher
    -0.07
    òi
    -0.07
    족
    -0.07
    arie
    -0.07
     Orthodox
    -0.07
     İslâm
    -0.07
    POSITIVE LOGITS
     political
    0.09
     secular
    0.09
    æĶ¿
    0.07
    sec
    0.07
     scientific
    0.07
     Science
    0.07
     Political
    0.07
     modern
    0.07
     Scientific
    0.06
     science
    0.06
    Activations Density 0.087%

    No Known Activations