© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106174
    Prev
    Next
    INDEX
    Explanations

    elements related to military command and communication

    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
    Ä±ÅŁÄ±k
    -0.07
    aiser
    -0.07
    uales
    -0.06
    ÙĪرات
    -0.06
    SizeMode
    -0.06
    ÃĹ↵↵
    -0.06
    aldo
    -0.06
    anca
    -0.06
    ernaut
    -0.06
    ẽ
    -0.06
    POSITIVE LOGITS
    istar
    0.08
     personally
    0.07
     orders
    0.07
     Tham
    0.06
    orders
    0.06
     formations
    0.06
     instructions
    0.06
     command
    0.06
     Orders
    0.06
     headquartered
    0.06
    Activations Density 0.055%

    No Known Activations