© 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. 44690
    Prev
    Next
    INDEX
    Explanations

    closing code blocks and statements

    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
     reg
    -0.10
    udo
    -0.09
     ing
    -0.09
    acre
    -0.09
     agr
    -0.09
    âĤ
    -0.08
     rue
    -0.08
    +
    -0.08
    heit
    -0.08
     kits
    -0.08
    POSITIVE LOGITS
    è¼
    0.11
    VisualStyle
    0.10
     GC
    0.10
    .MixedReality
    0.10
    .updateDynamic
    0.10
    -------------</
    0.10
    _vlog
    0.10
    .Undef
    0.10
     endwhile
    0.10
    >NN
    0.10
    Activations Density 0.009%

    No Known Activations