© 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. 5723
    Prev
    Next
    INDEX
    Explanations

    particulate matter, nitrogen, ozone

    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
     pencil
    -0.10
    -pencil
    -0.10
     contagious
    -0.09
     contaminated
    -0.09
     contamination
    -0.09
    FL
    -0.09
     Roch
    -0.08
     cashier
    -0.08
     extr
    -0.08
    nar
    -0.08
    POSITIVE LOGITS
     air
    0.26
     PM
    0.24
     sm
    0.23
     partic
    0.22
     Air
    0.20
     AQ
    0.19
    PM
    0.19
    AQ
    0.18
     pm
    0.17
     Visibility
    0.17
    Activations Density 0.035%

    No Known Activations