© 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. 726
    Prev
    Next
    INDEX
    Explanations

    company descriptions after "is a"

    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
     vign
    -0.09
    lop
    -0.09
    \Dependency
    -0.09
    à¸Ńร
    -0.09
     Cele
    -0.08
    Ｏ
    -0.08
    lops
    -0.08
    umm
    -0.08
    ocre
    -0.08
     à¸ģรà¸ģ
    -0.08
    POSITIVE LOGITS
     leading
    0.15
    imli
    0.12
    leading
    0.12
     proud
    0.12
     an
    0.11
     located
    0.11
     Leading
    0.10
    ä½įäºİ
    0.10
     pleased
    0.10
    located
    0.10
    Activations Density 0.078%

    No Known Activations