© 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. 56434
    Prev
    Next
    INDEX
    Explanations

    setting clear rules, goals, or boundaries

    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
    IfExists
    -0.10
     arada
    -0.09
    shal
    -0.09
    edl
    -0.09
    ä¸
    -0.09
     Instruments
    -0.09
     Guill
    -0.08
     cour
    -0.08
    osg
    -0.08
    642
    -0.08
    POSITIVE LOGITS
     длÑı
    0.13
     Äijá»ĥ
    0.12
     untuk
    0.11
    for
    0.11
     surrounding
    0.11
     for
    0.10
     dla
    0.10
     bagi
    0.10
     ourselves
    0.10
     ÑĩÑĤобÑĭ
    0.10
    Activations Density 0.105%

    No Known Activations