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. 44447
    Prev
    Next
    INDEX
    Explanations

    concerns related to civilian casualties during military operations

    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
    ynos
    -0.09
    ocoder
    -0.08
    CAT
    -0.07
     ì¼ĢìĿ´
    -0.07
    \Migration
    -0.07
    IBC
    -0.07
    uddy
    -0.07
    ellar
    -0.07
    inel
    -0.07
    UMB
    -0.07
    POSITIVE LOGITS
     Nine
    0.15
     Nin
    0.14
     Tik
    0.14
     Diy
    0.13
     Mosul
    0.13
     Kirk
    0.13
    Nine
    0.12
     Fall
    0.12
     Bai
    0.11
     Iraq
    0.09
    Activations Density 0.021%

    No Known Activations