© 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. 118034
    Prev
    Next
    INDEX
    Explanations

    references to international relations and cultural exchanges

    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
     american
    -0.09
     america
    -0.08
    ç¾İåĽ½
    -0.08
     СШÐIJ
    -0.08
     americ
    -0.08
     ç¾İåĽ½
    -0.08
    ç¾İåľĭ
    -0.08
     usa
    -0.07
     Mỹ
    -0.07
     America
    -0.07
    POSITIVE LOGITS
     overseas
    0.15
     foreign
    0.14
    foreign
    0.12
     abroad
    0.12
     Foreign
    0.11
     Overse
    0.10
    Foreign
    0.10
     FOREIGN
    0.10
    _foreign
    0.10
     yabancı
    0.08
    Activations Density 0.235%

    No Known Activations