© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5709
    Prev
    Next
    INDEX
    Explanations

    home DIY creation feasibility

    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
    Negative Logits
    OrDefault
    -0.10
     prelim
    -0.09
     Gibbs
    -0.09
     Cheat
    -0.09
     Fut
    -0.08
    ales
    -0.08
     def
    -0.08
    UMB
    -0.08
    usu
    -0.08
     Mayer
    -0.08
    POSITIVE LOGITS
     home
    0.39
     DIY
    0.34
    home
    0.30
    DI
    0.26
     thuis
    0.25
     diy
    0.25
     homemade
    0.23
    (home
    0.23
    -home
    0.23
    /home
    0.22
    Activations Density 0.188%

    No Known Activations