© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    job tasks and responsibilities

    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
     scheduling
    -0.11
     Hobby
    -0.09
     Schedule
    -0.09
    οκ
    -0.09
    ï¾ī
    -0.09
    ented
    -0.09
    ekim
    -0.08
     Scheduler
    -0.08
     amateur
    -0.08
     Gardner
    -0.08
    POSITIVE LOGITS
     tasks
    0.31
     assigned
    0.25
     duties
    0.25
     Tasks
    0.24
    tasks
    0.24
     task
    0.23
    ä»»åĬ¡
    0.23
    Tasks
    0.21
     responsibilities
    0.21
     assign
    0.21
    Activations Density 0.123%

    No Known Activations