© 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. 30445
    Prev
    Next
    INDEX
    Explanations

    conditional statements and logic

    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
    zin
    -0.08
    ãģ®ãģł
    -0.08
    507
    -0.08
     cabo
    -0.08
    alm
    -0.08
    sj
    -0.08
    567
    -0.08
    umann
    -0.08
     Brill
    -0.08
    .wp
    -0.08
    POSITIVE LOGITS
    reation
    0.10
     elif
    0.10
    DataExchange
    0.09
    SupportedContent
    0.09
     else
    0.09
    ControlEvents
    0.09
     ãĢĢ
    0.09
     Cust
    0.09
    OTS
    0.09
    createForm
    0.09
    Activations Density 0.009%

    No Known Activations