© 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. 53304
    Prev
    Next
    INDEX
    Explanations

    chemical products and services

    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
     Gut
    -0.11
    ennie
    -0.11
     Baz
    -0.10
    NSE
    -0.10
     gut
    -0.10
     lif
    -0.10
    asher
    -0.09
     CFL
    -0.09
    ansom
    -0.09
    muz
    -0.09
    POSITIVE LOGITS
     custom
    0.16
     Custom
    0.12
    custom
    0.12
     frac
    0.11
     tek
    0.10
     Rogers
    0.10
     Guardian
    0.10
     gallon
    0.10
     res
    0.10
     markets
    0.10
    Activations Density 0.124%

    No Known Activations