© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39252
    Prev
    Next
    INDEX
    Explanations

    code blocks and execution flow

    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
    .Companion
    -0.09
    _il
    -0.09
    lover
    -0.09
     æģ
    -0.09
    aval
    -0.09
     pestic
    -0.08
    799
    -0.08
     Lov
    -0.08
    ()=>
    -0.08
    ugi
    -0.08
    POSITIVE LOGITS
     try
    0.10
    :\n\n
    0.10
    oice
    0.09
     Myst
    0.09
    (async
    0.09
    :\n
    0.09
    ANE
    0.09
     tam
    0.08
    ênh
    0.08
    å¯Į
    0.08
    Activations Density 0.042%

    No Known Activations