© 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. 130582
    Prev
    Next
    INDEX
    Explanations

    references to students and educational 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
    ugi
    -0.07
    376
    -0.06
     discre
    -0.06
    uzey
    -0.06
    eto
    -0.06
    roleId
    -0.06
    byter
    -0.06
    destruct
    -0.06
    antro
    -0.05
    erva
    -0.05
    POSITIVE LOGITS
    .edu
    0.08
     students
    0.07
    -aged
    0.07
     GOODMAN
    0.07
    ÅĻÃŃž
    0.07
    -educated
    0.07
    ëĮĢíķĻêµIJ
    0.07
     college
    0.07
    quip
    0.07
     STUD
    0.07
    Activations Density 0.073%

    No Known Activations