© 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. 70850
    Prev
    Next
    INDEX
    Explanations

    country names and related geographical 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
    omo
    -0.06
    ÑĪев
    -0.06
    illis
    -0.06
    ior
    -0.06
    uent
    -0.06
    Chip
    -0.06
    asset
    -0.06
    illa
    -0.06
    illard
    -0.06
    ä¿
    -0.06
    POSITIVE LOGITS
     Seller
    0.08
    opup
    0.07
     seller
    0.07
    Seller
    0.07
    intage
    0.07
     Sellers
    0.06
    -item
    0.06
     زد
    0.06
    ëĿ¼ëıĦ
    0.06
    Trivia
    0.06
    Activations Density 0.019%

    No Known Activations