© 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. 27664
    Prev
    Next
    INDEX
    Explanations

    options followed by closing parenthesis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    633
    -0.10
    /he
    -0.09
     {|
    -0.09
     Kane
    -0.09
    æĻ
    -0.08
     Meyer
    -0.08
     Gut
    -0.08
    raphics
    -0.08
    tright
    -0.08
    oola
    -0.08
    POSITIVE LOGITS
    -Javadoc
    0.14
    lei
    0.10
     Maj
    0.09
    allis
    0.09
    =*/
    0.09
    aggable
    0.09
    gnore
    0.09
     amb
    0.08
    Ñĩики
    0.08
     âĶĢ
    0.08
    Activations Density 0.088%

    No Known Activations