© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35181
    Prev
    Next
    INDEX
    Explanations

    operation and function

    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
     ç¿
    -0.09
    ersh
    -0.09
    vore
    -0.09
    .PNG
    -0.09
    еÑĢим
    -0.08
    /Area
    -0.08
    fixture
    -0.08
    EFR
    -0.08
     Magnus
    -0.08
     tap
    -0.08
    POSITIVE LOGITS
     operation
    0.64
     functioning
    0.61
    operation
    0.48
     funcion
    0.46
     Operation
    0.43
     function
    0.42
    Operation
    0.39
    -operation
    0.38
     OPERATION
    0.37
     functionality
    0.36
    Activations Density 0.209%

    No Known Activations