© 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. 85734
    Prev
    Next
    INDEX
    Explanations

    terms related to workplace misconduct and regulatory actions

    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
    á»ĥ
    -0.07
    ¶Į
    -0.07
    Ïĩεί
    -0.07
     dah
    -0.07
    nám
    -0.07
    .Resize
    -0.07
     célib
    -0.07
     diplomacy
    -0.07
    baÅŁ
    -0.06
     ÙĨÙģ
    -0.06
    POSITIVE LOGITS
     regulators
    0.08
     Consumer
    0.08
     watchdog
    0.08
     regulator
    0.08
     investigating
    0.08
     consumer
    0.07
     investigations
    0.07
     investigation
    0.07
     regulatory
    0.07
     federal
    0.07
    Activations Density 0.077%

    No Known Activations