© 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. 10538
    Prev
    Next
    INDEX
    Explanations

    to initiate, put, legally, jail, simulate, expand, preprocess, stores

    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
    ¦æĥħ
    -0.12
    .Formatter
    -0.11
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.10
    ******č\n
    -0.10
    abcdefghijkl
    -0.10
    ¨ë¶Ģ
    -0.10
    ©©
    -0.10
    TRGL
    -0.09
    <|begin_of_text|>
    -0.09
    ldkf
    -0.09
    POSITIVE LOGITS
     .:
    0.08
    'gc
    0.08
    417
    0.08
     suce
    0.07
    -R
    0.07
     Jeb
    0.07
     poil
    0.07
    ignon
    0.07
    uffman
    0.07
     fist
    0.07
    Activations Density 0.026%

    No Known Activations