© 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. 19363
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients

    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
     salt
    -0.24
     salty
    -0.23
     salts
    -0.22
     Salt
    -0.21
    salt
    -0.21
    _salt
    -0.19
    Salt
    -0.19
     ÑģолÑĮ
    -0.14
     muá»iji
    -0.12
    å¡
    -0.10
    POSITIVE LOGITS
     oppon
    0.11
     Cure
    0.11
     pepper
    0.10
     optional
    0.10
    inez
    0.10
    LOPT
    0.09
     Cay
    0.09
     Pepper
    0.09
     Alleg
    0.09
    PPER
    0.09
    Activations Density 0.019%

    No Known Activations