Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44256
    Prev
    Next
    INDEX
    Explanations

    references to the Taliban and events related to their influence on education and rebuilding efforts

    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
     Sinai
    -0.07
    iterr
    -0.07
     ÛĮÙĩ
    -0.07
    æ´²
    -0.07
     Bahrain
    -0.07
     Palestin
    -0.07
     plá
    -0.07
    ptune
    -0.07
     Seas
    -0.07
     Suriye
    -0.07
    POSITIVE LOGITS
     Pas
    0.13
     muj
    0.12
     Tale
    0.12
     Kabul
    0.12
     Taliban
    0.12
     Muj
    0.11
     Afghan
    0.11
     Soviet
    0.11
     Soviets
    0.11
     Northern
    0.10
    Activations Density 0.011%

    No Known Activations