© 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 EvalsExportsinterp-engineNEWAPI 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. 62862
    Prev
    Next
    INDEX
    Explanations

    mentions of Jamaica and related terms

    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
    soever
    -0.07
    avigate
    -0.06
    lep
    -0.06
    891
    -0.06
     Albuquerque
    -0.06
    bie
    -0.06
    iÄĩ
    -0.06
    ÑĪив
    -0.06
    997
    -0.06
    859
    -0.06
    POSITIVE LOGITS
    ourt
    0.08
     Jama
    0.08
     Jamaica
    0.08
    -born
    0.07
    esson
    0.07
    gow
    0.07
    ITHER
    0.07
    ois
    0.07
     Kingston
    0.07
    apolis
    0.07
    Activations Density 0.013%

    No Known Activations