© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1468
    Prev
    Next
    INDEX
    Explanations

    the next

    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
     yesterday
    -0.15
     Yesterday
    -0.12
     Previous
    -0.11
    以æĿ¥
    -0.11
     since
    -0.11
     earlier
    -0.11
    Yesterday
    -0.10
     previous
    -0.10
     longest
    -0.10
    æĺ¨
    -0.09
    POSITIVE LOGITS
     next
    0.51
    next
    0.41
     nächsten
    0.37
     à¤ħà¤Ĺल
    0.32
    (next
    0.31
     coming
    0.30
    _next
    0.30
    -next
    0.29
    .next
    0.29
    Next
    0.28
    Activations Density 0.089%

    No Known Activations