© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 62036
    Prev
    Next
    INDEX
    Explanations

    Python code examples and solutions

    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
    ,application
    -0.10
     iterable
    -0.09
     :.:
    -0.09
     GetLastError
    -0.09
     chains
    -0.09
     CRUD
    -0.08
    å¼ĭ
    -0.08
    èİī
    -0.08
    ĵĺ
    -0.08
    .:.:
    -0.08
    POSITIVE LOGITS
     algorithm
    0.21
     solution
    0.20
     code
    0.16
     algorithms
    0.16
     function
    0.15
     approach
    0.14
    algorithm
    0.14
     solutions
    0.14
     Solution
    0.14
    Solution
    0.14
    Activations Density 0.263%

    No Known Activations