© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121326
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings, specifically admissions to the Bar and regulatory orders

    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
    erable
    -0.07
     Cover
    -0.06
     Goth
    -0.06
    iro
    -0.06
    uem
    -0.06
    enberg
    -0.06
     Suicide
    -0.06
    .AutoComplete
    -0.06
    æİĪ
    -0.06
    breaker
    -0.06
    POSITIVE LOGITS
    cheng
    0.07
    utter
    0.06
    DDL
    0.06
    uspend
    0.06
    iston
    0.06
     madrid
    0.06
     Lebens
    0.06
    ptom
    0.06
     licensee
    0.06
    ify
    0.06
    Activations Density 0.005%

    No Known Activations