© 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. 3314
    Prev
    Next
    INDEX
    Explanations

    programming class definitions

    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
    _classes
    -0.15
    FromClass
    -0.14
    Classes
    -0.13
     classes
    -0.12
    ClassName
    -0.12
    _class
    -0.11
    classes
    -0.11
    eel
    -0.11
    _CLASSES
    -0.11
     Classes
    -0.10
    POSITIVE LOGITS
    ä¼¼
    0.27
    ses
    0.27
    ifying
    0.24
    ifies
    0.24
    mate
    0.21
    (es
    0.21
    ically
    0.20
    ä¼¼çļĦ
    0.20
    ifiable
    0.19
    rooms
    0.18
    Activations Density 0.044%

    No Known Activations