© 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. 17-LLAMASCOPE-RES-131K
    11. 55651
    Prev
    Next
    INDEX
    Explanations

    references to various forms of art, specifically those related to Asian and Islamic cultures

    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
    ëĿ½
    -0.07
    emin
    -0.07
    OptionPane
    -0.07
    Ä©a
    -0.07
    íĦ
    -0.07
    Ïħγ
    -0.07
    oku
    -0.07
     dual
    -0.06
    blend
    -0.06
     иÑģк
    -0.06
    POSITIVE LOGITS
     nich
    0.07
     Tradition
    0.06
     Relief
    0.06
    airo
    0.06
    atism
    0.06
     genre
    0.06
     styles
    0.06
    afa
    0.06
     figur
    0.06
     Hubbard
    0.06
    Activations Density 0.035%

    No Known Activations