© 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. 33472
    Prev
    Next
    INDEX
    Explanations

    instance of class or matches

    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
    ëĭ¤ëĬĶ
    -0.11
    خاÙĨÙĩ
    -0.11
    OperationException
    -0.11
    run
    -0.10
    der
    -0.10
    åĿĬ
    -0.09
    adh
    -0.09
    turn
    -0.09
    runs
    -0.09
    IFn
    -0.09
    POSITIVE LOGITS
    aneously
    0.15
    aneous
    0.12
    (instance
    0.11
    /static
    0.11
    hood
    0.11
     of
    0.10
    egr
    0.10
    hower
    0.10
    iations
    0.10
     variables
    0.10
    Activations Density 0.023%

    No Known Activations