© 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. 54709
    Prev
    Next
    INDEX
    Explanations

    assistant: or author:

    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
    934
    -0.09
    assed
    -0.09
    unittest
    -0.08
    345
    -0.08
    PED
    -0.08
    ulus
    -0.08
    iker
    -0.08
     ÙĤØ·
    -0.08
    .MockMvc
    -0.08
     Ler
    -0.08
    POSITIVE LOGITS
    ship
    0.11
    gram
    0.10
    istor
    0.09
    ships
    0.09
    :
    0.09
     Buckingham
    0.09
    ç«
    0.09
    ttp
    0.08
    rompt
    0.08
    ARSE
    0.08
    Activations Density 0.024%

    No Known Activations