© 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. 38467
    Prev
    Next
    INDEX
    Explanations

    machines or equipment failures

    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
     leak
    -0.11
    Interceptor
    -0.09
     pist
    -0.09
     Gam
    -0.09
    leanup
    -0.09
    ecial
    -0.09
    olle
    -0.09
     rapes
    -0.09
    ptron
    -0.09
     Leak
    -0.09
    POSITIVE LOGITS
     failure
    0.29
     failures
    0.24
     Failure
    0.23
    failure
    0.21
    Failure
    0.20
     fail
    0.16
     FAILURE
    0.16
    fail
    0.16
     Fail
    0.16
    æķħ
    0.16
    Activations Density 0.069%

    No Known Activations