© 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. 18804
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons

    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
    iso
    -0.10
    .iso
    -0.10
     probably
    -0.09
    ppo
    -0.09
     beste
    -0.09
     Ris
    -0.09
    ila
    -0.09
    NULL
    -0.08
     Kra
    -0.08
    .IsNull
    -0.08
    POSITIVE LOGITS
     clearly
    0.16
     fail
    0.13
     fails
    0.13
     FAIL
    0.12
     Clearly
    0.11
    æĺİ
    0.11
     failed
    0.11
    igger
    0.11
    .fail
    0.10
    viol
    0.10
    Activations Density 0.111%

    No Known Activations