© 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. 43067
    Prev
    Next
    INDEX
    Explanations

    predict, analyze, identify

    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
     Borrow
    -0.09
     Jelly
    -0.09
     slee
    -0.09
     Toni
    -0.09
     arrested
    -0.09
    anny
    -0.08
     Kirk
    -0.08
    oni
    -0.08
     Redistribution
    -0.08
    python
    -0.08
    POSITIVE LOGITS
     suggest
    0.15
     automatically
    0.14
     suggested
    0.13
     help
    0.13
     suggesting
    0.13
     flag
    0.13
     recommend
    0.12
     assist
    0.12
     suggests
    0.12
     suggestions
    0.12
    Activations Density 0.100%

    No Known Activations