© 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. 15-LLAMASCOPE-RES-131K
    11. 88853
    Prev
    Next
    INDEX
    Explanations

    topics related to religious and cultural groups, with a focus on Catholicism

    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
    antity
    -0.08
     nues
    -0.08
    rone
    -0.07
    InView
    -0.07
    anford
    -0.07
    ialect
    -0.06
     dashes
    -0.06
    .UnitTesting
    -0.06
    HomeAsUp
    -0.06
    DOMNode
    -0.06
    POSITIVE LOGITS
    ibu
    0.06
     Mitar
    0.06
    ertino
    0.06
    erts
    0.06
    egg
    0.06
    .Accessible
    0.06
     foremost
    0.06
    ),
    0.06
     Sap
    0.05
     fright
    0.05
    Activations Density 0.050%

    No Known Activations