Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43394
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to international relations and formal agreements

    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
     honorable
    -0.08
     honors
    -0.07
    -colored
    -0.07
     theater
    -0.07
     colored
    -0.07
     honored
    -0.07
     Armor
    -0.07
     flavored
    -0.07
    favor
    -0.06
     Kendrick
    -0.06
    POSITIVE LOGITS
     WTO
    0.14
     NAFTA
    0.11
     Party
    0.11
     Parties
    0.10
     mult
    0.10
     exporters
    0.09
     imports
    0.09
     exporting
    0.09
     exports
    0.08
    Party
    0.08
    Activations Density 0.001%

    No Known Activations