© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 55659
    Prev
    Next
    INDEX
    Explanations

    terms related to disability and family medical leave issues

    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
    å¯Ħ
    -0.07
    imler
    -0.07
    кÑĥÑĢ
    -0.07
    AndWait
    -0.07
    ABCDE
    -0.07
    ãĤ¹ãĤ¯
    -0.07
    æĪIJ人
    -0.06
    raç
    -0.06
    iage
    -0.06
    ounge
    -0.06
    POSITIVE LOGITS
     medical
    0.08
     FML
    0.08
     disability
    0.07
     Sick
    0.07
     sick
    0.07
    medical
    0.07
     Medical
    0.07
     sickness
    0.07
     employee
    0.07
     Employee
    0.07
    Activations Density 0.006%

    No Known Activations