© 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. 5519
    Prev
    Next
    INDEX
    Explanations

    Explanation:

    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
     Advance
    -0.10
    azes
    -0.09
     Koch
    -0.09
     intrusive
    -0.09
     Wing
    -0.09
     inne
    -0.08
    Advance
    -0.08
     suce
    -0.08
     Proto
    -0.08
    oin
    -0.08
    POSITIVE LOGITS
    ä»Ķ
    0.11
    nze
    0.10
     answer
    0.09
     Yes
    0.09
    ertino
    0.09
     yes
    0.09
     reasoning
    0.09
    CEE
    0.09
    _reason
    0.09
     feedback
    0.08
    Activations Density 0.010%

    No Known Activations