© 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. 32844
    Prev
    Next
    INDEX
    Explanations

    bromo compounds

    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
     Belt
    -0.11
    elman
    -0.11
    Biz
    -0.10
    bett
    -0.10
    belt
    -0.09
     Barcl
    -0.09
    Blueprint
    -0.09
     Basil
    -0.09
     Bacon
    -0.09
     çº
    -0.09
    POSITIVE LOGITS
     Br
    0.30
     brom
    0.28
    Br
    0.26
     Brom
    0.24
     hal
    0.23
     br
    0.22
     Hal
    0.19
    .Br
    0.19
    hal
    0.18
     halo
    0.18
    Activations Density 0.085%

    No Known Activations