© 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. 55279
    Prev
    Next
    INDEX
    Explanations

    structural breaks followed by content

    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
    atta
    -0.10
    aina
    -0.10
    agh
    -0.10
     fore
    -0.10
     Shah
    -0.09
    966
    -0.09
    bal
    -0.09
     Cem
    -0.09
     bl
    -0.09
    amar
    -0.09
    POSITIVE LOGITS
     огÑĢа
    0.10
     %#
    0.10
     Seam
    0.09
    ichel
    0.09
    772
    0.09
    aire
    0.09
     riv
    0.09
    anou
    0.09
    =cut
    0.09
    presso
    0.09
    Activations Density 0.091%

    No Known Activations