© 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. 47568
    Prev
    Next
    INDEX
    Explanations

    but ... notice

    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
    dio
    -0.10
     gas
    -0.09
    elter
    -0.09
    çŀ¬
    -0.09
     weap
    -0.09
     sometimes
    -0.09
    |/
    -0.09
    è±
    -0.09
     Gas
    -0.08
     nowhere
    -0.08
    POSITIVE LOGITS
     couldn
    0.16
    couldn
    0.14
     Unable
    0.13
    æĹłæ³ķ
    0.13
     Couldn
    0.13
     surre
    0.13
    Couldn
    0.12
     stealing
    0.12
     cannot
    0.12
     steal
    0.12
    Activations Density 0.015%

    No Known Activations