© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 359
    Prev
    Next
    INDEX
    Explanations

    content related to locations and geographic references, particularly in Europe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions and connecting words that establish geographical relationships between Europe/European countries and other locations, often in contexts discussing international travel, cultural comparisons, or cross-border activities.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     american
    -0.09
     americ
    -0.09
     america
    -0.09
     America
    -0.08
    ãĤ¢ãĥ¡ãĥªãĤ«
    -0.08
     American
    -0.07
    american
    -0.07
     Americas
    -0.07
     Americans
    -0.07
    -American
    -0.07
    POSITIVE LOGITS
     European
    0.15
     Europeans
    0.15
     Europe
    0.14
    European
    0.13
    Europe
    0.13
     overseas
    0.13
     europé
    0.13
     foreign
    0.12
     europe
    0.12
    欧
    0.12
    Activations Density 0.338%

    No Known Activations