© 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. 16447
    Prev
    Next
    INDEX
    Explanations

    references to Caribbean cuisine and cultural elements

    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
     Kazakhstan
    -0.07
     Alpine
    -0.07
     Mongolia
    -0.07
     Yosemite
    -0.07
     Tibetan
    -0.07
     Siber
    -0.07
    California
    -0.07
    antar
    -0.07
    onen
    -0.07
     Riverside
    -0.07
    POSITIVE LOGITS
     Caribbean
    0.19
     island
    0.14
     Jamaica
    0.13
     Trinidad
    0.13
     Hait
    0.12
     Jama
    0.11
     Bahamas
    0.11
    ibbean
    0.11
     Coconut
    0.11
     Island
    0.10
    Activations Density 0.144%

    No Known Activations