© 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. 86797
    Prev
    Next
    INDEX
    Explanations

    references to military actions and geopolitical events

    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
    ÑĢиÑĤи
    -0.08
    اÙĪت
    -0.07
    iaux
    -0.07
    gren
    -0.07
    .freeze
    -0.07
    emodel
    -0.07
    _KP
    -0.07
    æĢ§
    -0.06
    Borders
    -0.06
    æĢ§çļĦ
    -0.06
    POSITIVE LOGITS
     airspace
    0.10
     hovering
    0.08
     above
    0.08
     air
    0.07
     orbit
    0.07
    orbit
    0.07
     hovered
    0.07
    _hover
    0.07
     close
    0.07
     над
    0.07
    Activations Density 0.116%

    No Known Activations