© 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 EvalsExportsinterp-engineNEWAPI 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. 70193
    Prev
    Next
    INDEX
    Explanations

    connections between legal work, community engagement, and nonprofit organizations

    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
    ĶåĽŀ
    -0.08
     UNIVERSITY
    -0.07
    ãĤ¹ãĤ¿ãĥ¼
    -0.07
     UNIVERS
    -0.07
     Harvard
    -0.07
    .Reporting
    -0.07
    大åѦ
    -0.07
    सà¤Ń
    -0.07
     sÆ°
    -0.07
    veau
    -0.07
    POSITIVE LOGITS
     industry
    0.10
    industry
    0.08
     practitioner
    0.08
     professional
    0.08
     Industry
    0.07
     professionals
    0.07
     practitioners
    0.07
     practicing
    0.06
     practice
    0.06
     commercial
    0.06
    Activations Density 0.052%

    No Known Activations