© 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. 62121
    Prev
    Next
    INDEX
    Explanations

    pass down traditions and data

    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
     sister
    -0.11
     Sister
    -0.10
     infancy
    -0.09
     otp
    -0.09
     peripheral
    -0.09
     Lew
    -0.08
     bidi
    -0.08
    ogg
    -0.08
    .preview
    -0.08
    chu
    -0.08
    POSITIVE LOGITS
     passed
    0.44
     Passed
    0.36
    ä¼ł
    0.34
    passed
    0.34
     passing
    0.33
    Passed
    0.33
     passes
    0.32
     transmission
    0.31
     truyá»ģn
    0.29
    åĤ³
    0.29
    Activations Density 0.088%

    No Known Activations