© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 50965
    Prev
    Next
    INDEX
    Explanations

    retirement state or activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Äijá»ĵ
    -0.09
     Gur
    -0.09
     graduating
    -0.09
     ACM
    -0.09
     Smy
    -0.08
    flen
    -0.08
     wages
    -0.08
    ¨
    -0.08
     resultList
    -0.08
     departing
    -0.08
    POSITIVE LOGITS
     retirement
    0.50
     retired
    0.48
     retire
    0.46
     Retirement
    0.37
    éĢĢ
    0.31
     retir
    0.31
    à¹Ģà¸ģษ
    0.28
     retirees
    0.28
    Ret
    0.25
     retiring
    0.25
    Activations Density 0.072%

    No Known Activations