© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 28829
    Prev
    Next
    INDEX
    Explanations

    after it is

    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
     then
    -0.09
     THEN
    -0.09
    then
    -0.08
     Then
    -0.08
    olds
    -0.08
    rael
    -0.08
     ÑĤогда
    -0.08
     entonces
    -0.08
     nhá»Ŀ
    -0.08
    Neal
    -0.08
    POSITIVE LOGITS
     during
    0.44
     when
    0.37
    during
    0.33
    when
    0.30
     durante
    0.29
     During
    0.27
     ÙĩÙĨگاÙħ
    0.26
     lors
    0.25
     khi
    0.25
     bÄĽhem
    0.24
    Activations Density 0.347%

    No Known Activations