© 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. 10589
    Prev
    Next
    INDEX
    Explanations

    lost in

    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
    zan
    -0.11
    indh
    -0.10
    abwe
    -0.10
     âĹĦ
    -0.10
    569
    -0.09
    GED
    -0.09
    ableViewController
    -0.09
    809
    -0.09
    plier
    -0.08
     Gan
    -0.08
    POSITIVE LOGITS
     track
    0.16
     sight
    0.16
     mát
    0.14
     lost
    0.13
    lost
    0.13
     Lost
    0.12
     touch
    0.12
     somewhere
    0.11
    orage
    0.11
     wages
    0.11
    Activations Density 0.015%

    No Known Activations