© 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. 10769
    Prev
    Next
    INDEX
    Explanations

    then begin or can do

    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
    çİ°åľ¨
    -0.11
     now
    -0.11
    now
    -0.09
    .:.
    -0.09
     rej
    -0.09
    stoff
    -0.09
    :::::
    -0.08
     Twe
    -0.08
    turnstile
    -0.08
     repr
    -0.08
    POSITIVE LOGITS
     THEN
    0.38
     then
    0.29
    THEN
    0.27
    æīį
    0.23
     ÑĤогда
    0.22
     Then
    0.22
    then
    0.22
    Then
    0.21
     então
    0.20
     entonces
    0.20
    Activations Density 0.105%

    No Known Activations