© 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. 8923
    Prev
    Next
    INDEX
    Explanations

    apology or not sure

    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
    crast
    -0.10
     íĭ
    -0.09
     until
    -0.09
    arna
    -0.09
     Gaw
    -0.09
     AD
    -0.09
    case
    -0.08
    彡
    -0.08
    ucas
    -0.08
     Drew
    -0.08
    POSITIVE LOGITS
     cut
    0.21
     cutoff
    0.20
    cut
    0.16
     CUT
    0.16
     cutting
    0.16
     Cut
    0.16
     incomplete
    0.16
     cắt
    0.16
    _TRUNC
    0.15
    .cut
    0.15
    Activations Density 0.058%

    No Known Activations