© 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. 19339
    Prev
    Next
    INDEX
    Explanations

    fascinating or content should help

    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
     ​​
    -0.09
    .habbo
    -0.09
     Ä°mpar
    -0.08
    ãĤ¹ãĥ¬
    -0.08
    hiba
    -0.08
    ughty
    -0.08
    ÑĽ
    -0.08
    krv
    -0.08
    redient
    -0.08
    turnstile
    -0.07
    POSITIVE LOGITS
    ________
    0.07
     Vent
    0.07
     [](
    0.07
    osi
    0.07
     ifndef
    0.07
     eldre
    0.07
    heimer
    0.07
     Ach
    0.07
    elix
    0.07
     trh
    0.07
    Activations Density 0.337%

    No Known Activations