© 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. 125642
    Prev
    Next
    INDEX
    Explanations

    highly active verbs and significant entities related to leadership and organization

    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
     Imported
    -0.08
     Nationwide
    -0.07
     nationwide
    -0.07
     imported
    -0.07
     federal
    -0.06
     Alabama
    -0.06
     Connecticut
    -0.06
     ülkenin
    -0.06
     Hawaii
    -0.06
     importer
    -0.06
    POSITIVE LOGITS
     global
    0.20
     worldwide
    0.17
    global
    0.17
     Global
    0.17
     globally
    0.15
     GLOBAL
    0.15
    -global
    0.15
    Global
    0.15
    _Global
    0.15
     world
    0.14
    Activations Density 0.004%

    No Known Activations