© 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. 44632
    Prev
    Next
    INDEX
    Explanations

    quality of teaching urban higher

    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
    404
    -0.09
    lvl
    -0.09
     Arte
    -0.09
    672
    -0.09
    729
    -0.09
    596
    -0.08
    arine
    -0.08
    >*</
    -0.08
    421
    -0.08
    uard
    -0.08
    POSITIVE LOGITS
     output
    0.14
     mercy
    0.13
     craftsmanship
    0.12
     execution
    0.12
     services
    0.12
     service
    0.11
     fit
    0.11
     ζÏī
    0.11
     life
    0.11
     outputs
    0.11
    Activations Density 0.048%

    No Known Activations