© 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. 30544
    Prev
    Next
    INDEX
    Explanations

    federated learning

    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
     thao
    -0.10
    IPH
    -0.10
    ï½°
    -0.09
    chsel
    -0.09
    ConverterFactory
    -0.09
     Seas
    -0.08
    åµ
    -0.08
    Legacy
    -0.08
     prote
    -0.08
    iou
    -0.08
    POSITIVE LOGITS
     distributed
    0.22
     Distributed
    0.21
    distributed
    0.18
     parallel
    0.15
    åĪĨå¸ĥ
    0.15
    istributed
    0.14
    _MPI
    0.14
     communication
    0.13
     dist
    0.13
     Communication
    0.13
    Activations Density 0.031%

    No Known Activations