© 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. 32673
    Prev
    Next
    INDEX
    Explanations

    while connecting clauses

    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
    ests
    -0.10
    etes
    -0.09
    illon
    -0.09
    etu
    -0.09
    ellas
    -0.08
    faker
    -0.08
    anz
    -0.08
    oved
    -0.08
    phia
    -0.08
     remot
    -0.08
    POSITIVE LOGITS
     simult
    0.15
    åIJĮæĻĤ
    0.14
    s
    0.14
    åIJĮæŶ
    0.14
     simultaneously
    0.14
     others
    0.12
    dess
    0.12
     однов
    0.12
     meantime
    0.12
    Meanwhile
    0.11
    Activations Density 0.025%

    No Known Activations