© 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. 56097
    Prev
    Next
    INDEX
    Explanations

    terms related to Korean cuisine and its cultural significance

    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
    ptron
    -0.08
    ırak
    -0.07
    ολ
    -0.07
     æ©
    -0.07
    indre
    -0.07
     desi
    -0.06
    aney
    -0.06
     Laurie
    -0.06
    iasi
    -0.06
    ddit
    -0.06
    POSITIVE LOGITS
    atoms
    0.07
     Hong
    0.06
     Cambodia
    0.06
     Flood
    0.06
     Camb
    0.06
    óng
    0.06
    uels
    0.06
     Hu
    0.06
     Eisen
    0.06
     SEG
    0.06
    Activations Density 0.038%

    No Known Activations