© 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. 116472
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fired" along with related terms indicating termination of employment

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    éry
    -0.07
     Netz
    -0.07
    ÙĨÚ¯ÛĮ
    -0.07
    ValuePair
    -0.07
    शन
    -0.07
     Hed
    -0.06
    führ
    -0.06
    691
    -0.06
     Collapse
    -0.06
    withdraw
    -0.06
    POSITIVE LOGITS
     employees
    0.07
     khá»ıi
    0.07
    æİī
    0.07
     employment
    0.07
     Employment
    0.07
     employed
    0.07
     hired
    0.06
     redundancy
    0.06
     Employees
    0.06
     ì§ģ
    0.06
    Activations Density 0.009%

    No Known Activations