© 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. 64710
    Prev
    Next
    INDEX
    Explanations

    Pascals

    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
    udder
    -0.09
    pector
    -0.09
     Duy
    -0.09
     Duffy
    -0.09
     Eigen
    -0.09
    uen
    -0.09
    ilos
    -0.08
     éĢ
    -0.08
     Burr
    -0.08
    éri
    -0.08
    POSITIVE LOGITS
     pressure
    0.36
     Pressure
    0.32
     pressures
    0.29
    Pressure
    0.29
    pressure
    0.27
    -pressure
    0.23
    _pressure
    0.22
     Pascal
    0.21
     bar
    0.21
    åİĭ
    0.20
    Activations Density 0.025%

    No Known Activations