© 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. 11473
    Prev
    Next
    INDEX
    Explanations

    you need to

    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
    æīįèĥ½
    -0.11
     нелÑĮзÑı
    -0.10
    ought
    -0.09
    ầm
    -0.09
     можно
    -0.09
    acco
    -0.09
     mainstream
    -0.09
     famed
    -0.08
     Halk
    -0.08
     pan
    -0.08
    POSITIVE LOGITS
     need
    0.21
    éľĢè¦ģ
    0.19
     needs
    0.17
     cần
    0.16
     first
    0.15
    need
    0.15
    'll
    0.14
    ’;ll
    0.14
     requires
    0.14
     require
    0.13
    Activations Density 0.076%

    No Known Activations