© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24676
    Prev
    Next
    INDEX
    Explanations

    writing a letter

    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
     elit
    -0.09
     Messaging
    -0.09
     mailing
    -0.09
    kek
    -0.09
     messaging
    -0.09
    лива
    -0.08
     acknowled
    -0.08
    emas
    -0.08
    sty
    -0.08
     MessageBoxButtons
    -0.08
    POSITIVE LOGITS
     letter
    0.19
    letter
    0.16
     LETTER
    0.15
    -letter
    0.14
     Letter
    0.14
    (letter
    0.13
    Letter
    0.13
     rog
    0.13
    dated
    0.13
     letters
    0.13
    Activations Density 0.069%

    No Known Activations