© 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. 84836
    Prev
    Next
    INDEX
    Explanations

    references to military groups and political structures

    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
    βολή
    -0.08
    koli
    -0.08
    æĪ¸
    -0.07
    .onView
    -0.07
    ,...↵↵
    -0.07
    енз
    -0.07
    ìŀ¥ìĿĢ
    -0.07
    è§Ĵèī²
    -0.07
    çiler
    -0.07
    หาร
    -0.07
    POSITIVE LOGITS
    人çļĦ
    0.15
    ’s
    0.14
    's
    0.14
    èĢħçļĦ
    0.14
    家çļĦ
    0.13
    åĬĽçļĦ
    0.12
    çĶŁçļĦ
    0.11
    åŃIJçļĦ
    0.11
    ìŀIJìĿĺ
    0.11
    ìĤ¬ìĿĺ
    0.10
    Activations Density 0.217%

    No Known Activations