© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 478
    Prev
    Next
    INDEX
    Explanations

    jobs and job creation

    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
     occupational
    -0.11
     Occupational
    -0.10
     Profession
    -0.09
     autopsy
    -0.09
     Cow
    -0.09
     profession
    -0.09
     recruiter
    -0.08
     Freeman
    -0.08
     saddle
    -0.08
    .Builder
    -0.08
    POSITIVE LOGITS
     jobs
    0.46
     Jobs
    0.33
    jobs
    0.33
    Jobs
    0.29
     job
    0.29
     employment
    0.27
    _jobs
    0.24
    .jobs
    0.23
    job
    0.20
     positions
    0.19
    Activations Density 0.035%

    No Known Activations