© 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. 61045
    Prev
    Next
    INDEX
    Explanations

    expressions of faith and spiritual 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
    okit
    -0.08
    printStats
    -0.07
    ManagerInterface
    -0.07
    оÑĢони
    -0.07
    iker
    -0.07
    umper
    -0.07
    quan
    -0.07
    rons
    -0.07
    ainter
    -0.07
    ForResource
    -0.07
    POSITIVE LOGITS
     Bell
    0.07
    ansion
    0.06
     Bing
    0.06
    lint
    0.06
    Modern
    0.06
     chilling
    0.06
     Modern
    0.06
    Bell
    0.06
     notice
    0.06
     modern
    0.06
    Activations Density 0.061%

    No Known Activations