© 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. 263
    Prev
    Next
    INDEX
    Explanations

    financial sector and large shareholders

    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
     consum
    -0.10
     brokers
    -0.09
     Cycl
    -0.09
    517
    -0.09
    cheon
    -0.09
    浪
    -0.09
     specifier
    -0.09
    .newBuilder
    -0.08
     Illum
    -0.08
     stocks
    -0.08
    POSITIVE LOGITS
     asset
    0.24
     custody
    0.21
     fund
    0.21
     cust
    0.19
    asset
    0.19
     fee
    0.18
     Asset
    0.18
    Asset
    0.17
     fid
    0.17
     investment
    0.16
    Activations Density 0.102%

    No Known Activations