© 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. 9-LLAMASCOPE-RES-131K
    11. 96984
    Prev
    Next
    INDEX
    Explanations

    references to spiritual or religious journeys and experiences

    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
    ongan
    -0.07
    lish
    -0.07
    APS
    -0.07
    gne
    -0.07
    yd
    -0.07
    eco
    -0.07
    fü
    -0.07
     بÙĪابة
    -0.07
    'https
    -0.07
    OCR
    -0.07
    POSITIVE LOGITS
    -like
    0.09
    ĺ认
    0.07
    like
    0.07
     shock
    0.06
    igin
    0.06
    asto
    0.06
    çļ
    0.06
     ëĵ¯
    0.06
     Clay
    0.06
     اÙĦرÙħ
    0.06
    Activations Density 0.073%

    No Known Activations