© 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. 33352
    Prev
    Next
    INDEX
    Explanations

    then, recursively

    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
    .Before
    -0.10
     lasting
    -0.10
    589
    -0.08
    -lasting
    -0.08
     initially
    -0.08
    uda
    -0.07
     Before
    -0.07
    Initially
    -0.07
    à¸Ńà¸ģà¸Īาà¸ģ
    -0.07
     Now
    -0.07
    POSITIVE LOGITS
     then
    0.90
    then
    0.71
     Then
    0.70
     THEN
    0.68
    Then
    0.68
    çĦ¶åIJİ
    0.62
     заÑĤем
    0.58
    ï¼ĮçĦ¶åIJİ
    0.54
    _then
    0.54
     سپس
    0.53
    Activations Density 0.476%

    No Known Activations