© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34978
    Prev
    Next
    INDEX
    Explanations

    your day job

    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
     vocational
    -0.10
     occupational
    -0.10
    ouz
    -0.09
     Idle
    -0.09
    077
    -0.09
    anken
    -0.09
     Occupational
    -0.08
    αÏĤ
    -0.08
    _probe
    -0.08
     prer
    -0.08
    POSITIVE LOGITS
     jobs
    0.45
     job
    0.45
    job
    0.34
     Jobs
    0.33
    jobs
    0.33
     Job
    0.31
     JOB
    0.29
    Job
    0.29
    _job
    0.26
    Jobs
    0.26
    Activations Density 0.091%

    No Known Activations