© 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. 54354
    Prev
    Next
    INDEX
    Explanations

    she opened

    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
     drying
    -0.10
     Kore
    -0.10
    caught
    -0.09
    âĪ§
    -0.09
    _compress
    -0.09
    upe
    -0.09
    éĸī
    -0.09
     cup
    -0.09
     caught
    -0.09
     Collect
    -0.09
    POSITIVE LOGITS
     opened
    0.36
    æīĵå¼Ģ
    0.33
     opening
    0.32
     opens
    0.29
    ãĤĴéĸĭ
    0.28
    -opening
    0.27
    opened
    0.27
     open
    0.27
     Opening
    0.26
    opening
    0.26
    Activations Density 0.074%

    No Known Activations