© 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. 54710
    Prev
    Next
    INDEX
    Explanations

    loop calculations

    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
     unp
    -0.09
     overdue
    -0.09
    à¸Ķร
    -0.09
     irreversible
    -0.08
    anno
    -0.08
    kening
    -0.08
    ÂĢÂĢ
    -0.08
     ëijIJ
    -0.08
     Strand
    -0.08
     permanent
    -0.08
    POSITIVE LOGITS
     loop
    0.33
    循
    0.26
    loop
    0.25
     Loop
    0.24
     loops
    0.24
    -loop
    0.23
    Loop
    0.22
    _loop
    0.22
    .loop
    0.19
     LOOP
    0.19
    Activations Density 0.202%

    No Known Activations