© 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. 128917
    Prev
    Next
    INDEX
    Explanations

    names of universities and higher education institutions

    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
    chten
    -0.08
    iad
    -0.07
    Ïįν
    -0.07
    kov
    -0.06
    Ñĩие
    -0.06
    aren
    -0.06
    sled
    -0.06
    ekil
    -0.06
    YNAMIC
    -0.06
    kontakte
    -0.06
    POSITIVE LOGITS
     University
    0.14
    大åѦ
    0.11
    .edu
    0.10
    ëĮĢíķĻêµIJ
    0.10
    University
    0.10
     university
    0.10
    大åѸ
    0.10
     UNIVERSITY
    0.09
     Ãľniversitesi
    0.09
     College
    0.08
    Activations Density 0.059%

    No Known Activations