© 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. 15-LLAMASCOPE-RES-131K
    11. 151
    Prev
    Next
    INDEX
    Explanations

    aspects of spirituality and religion that connect to social and community themes

    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
    è³¢
    -0.07
    aji
    -0.07
    ÑĤÑİ
    -0.06
    ên
    -0.06
    erial
    -0.06
    جاÙĨ
    -0.06
    .sponge
    -0.06
    ç
    -0.06
    cial
    -0.06
    iales
    -0.06
    POSITIVE LOGITS
     confines
    0.11
     bounds
    0.11
     framework
    0.10
     context
    0.09
    within
    0.09
     within
    0.09
     frame
    0.09
     Within
    0.08
     frameworks
    0.08
    Within
    0.08
    Activations Density 0.061%

    No Known Activations