© 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. 64765
    Prev
    Next
    INDEX
    Explanations

    such as chips, broccoli, kale, eggs

    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
     аж
    -0.10
     Nab
    -0.09
     sometimes
    -0.09
    krv
    -0.09
     dessert
    -0.09
     lax
    -0.09
     nab
    -0.09
     refresh
    -0.09
    _HOR
    -0.08
     ASCII
    -0.08
    POSITIVE LOGITS
     fruits
    0.15
     doom
    0.10
    lege
    0.10
     fruit
    0.10
     salmon
    0.10
     leaf
    0.09
    ruits
    0.09
     berries
    0.09
    yw
    0.09
     chicken
    0.09
    Activations Density 0.070%

    No Known Activations