© 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. 59666
    Prev
    Next
    INDEX
    Explanations

    the top of

    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
     Elev
    -0.10
    abin
    -0.09
     elev
    -0.09
     backs
    -0.09
    éł
    -0.09
    uisse
    -0.09
     Townsend
    -0.08
    321
    -0.08
    797
    -0.08
    åŀĤ
    -0.08
    POSITIVE LOGITS
     top
    0.57
    top
    0.45
    顶
    0.42
    -top
    0.38
    éłĤ
    0.37
    _top
    0.36
    \ttop
    0.34
    .top
    0.34
    (top
    0.31
    Top
    0.29
    Activations Density 0.124%

    No Known Activations