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. 44252
    Prev
    Next
    INDEX
    Explanations

    phrases related to governance and community development efforts

    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
    enberg
    -0.06
    anship
    -0.06
    ÌĨ
    -0.06
    zan
    -0.06
    eldorf
    -0.06
     trá»Ŀi
    -0.06
     glob
    -0.06
     Advertising
    -0.05
    estar
    -0.05
     Intelligence
    -0.05
    POSITIVE LOGITS
     demands
    0.15
     demand
    0.12
     grievances
    0.12
     Demand
    0.10
    demand
    0.09
     rightful
    0.09
     aspirations
    0.09
     demanded
    0.09
    -demand
    0.08
     genuine
    0.08
    Activations Density 0.019%

    No Known Activations