© 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. 9044
    Prev
    Next
    INDEX
    Explanations

    And who, As I, Of course!

    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
     TRUE
    -0.10
     true
    -0.10
     fuck
    -0.09
    owie
    -0.09
     True
    -0.09
    Unchecked
    -0.09
     fucked
    -0.09
     FUCK
    -0.09
     bast
    -0.09
     bastard
    -0.09
    POSITIVE LOGITS
     obvious
    0.13
     Waste
    0.11
    åºŁ
    0.10
     gr
    0.10
    STATE
    0.10
     riv
    0.10
    ÑĢаÑĤиÑĤÑĮ
    0.10
    oser
    0.10
    ilt
    0.10
     wasting
    0.10
    Activations Density 0.052%

    No Known Activations