© 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. 84388
    Prev
    Next
    INDEX
    Explanations

    terms associated with religious liturgical practices and their significance

    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
     scriptures
    -0.06
     raw
    -0.05
     population
    -0.05
    ansa
    -0.05
    980
    -0.05
    838
    -0.05
    eki
    -0.05
     Failed
    -0.05
    apon
    -0.05
    дам
    -0.05
    POSITIVE LOGITS
     lit
    0.10
    OrNil
    0.08
     ç¤
    0.08
    ungen
    0.08
     vest
    0.07
    unge
    0.07
    ại
    0.07
    oyal
    0.07
     Vest
    0.07
     Lit
    0.07
    Activations Density 0.017%

    No Known Activations