© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64078
    Prev
    Next
    INDEX
    Explanations

    parameters, algorithms, architecture, errors

    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
    data
    -0.11
     dataset
    -0.11
     data
    -0.11
    hir
    -0.11
     datasets
    -0.11
    è³ĩæĸĻ
    -0.10
    dataset
    -0.10
    æķ°æį®
    -0.10
    bases
    -0.10
    _dataset
    -0.10
    POSITIVE LOGITS
     algorithms
    0.13
     algorithm
    0.12
    ç®Ĺ
    0.11
     processing
    0.10
    algorithm
    0.10
     objectives
    0.09
     techniques
    0.09
     اÙĦÙħÙĩÙĨØ©
    0.09
    æł¡
    0.09
     hardware
    0.09
    Activations Density 0.077%

    No Known Activations