© 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. 19351
    Prev
    Next
    INDEX
    Explanations

    ensuring correctness or proper state

    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
    674
    -0.12
     Guth
    -0.10
    472
    -0.10
     simply
    -0.09
     Mim
    -0.09
     neither
    -0.09
    ifen
    -0.09
    ava
    -0.08
     accompl
    -0.08
    074
    -0.08
    POSITIVE LOGITS
     proper
    0.18
     correct
    0.17
     properly
    0.16
    proper
    0.15
     Proper
    0.15
    æŃ£ç¡®
    0.15
     Äijúng
    0.14
     correctly
    0.14
    correct
    0.13
     consistent
    0.12
    Activations Density 0.050%

    No Known Activations