© 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. 50208
    Prev
    Next
    INDEX
    Explanations

    data breakdown and reporting

    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
    âĶĶ
    -0.10
     Ratings
    -0.10
    /background
    -0.09
    acomment
    -0.09
    надлеж
    -0.09
     aggregated
    -0.09
     gratuiti
    -0.09
    ä¾¡æł¼
    -0.09
    urovision
    -0.09
    fea
    -0.09
    POSITIVE LOGITS
     breakdown
    0.22
     report
    0.19
     total
    0.18
     per
    0.16
     Report
    0.16
     pie
    0.15
     Total
    0.15
     summary
    0.15
     reports
    0.15
     statistics
    0.15
    Activations Density 0.221%

    No Known Activations