© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35299
    Prev
    Next
    INDEX
    Explanations

    connects clauses

    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
    éĺħ读次æķ°
    -0.08
     :\n\n\n\n
    -0.08
    olumn
    -0.08
    _AUX
    -0.08
    gd
    -0.07
    nyder
    -0.07
    ylland
    -0.07
    umbn
    -0.07
    'gc
    -0.07
    quin
    -0.07
    POSITIVE LOGITS
     which
    0.12
     Which
    0.12
     especially
    0.10
     BUT
    0.10
     so
    0.10
    which
    0.10
    alth
    0.10
    Which
    0.10
    so
    0.09
     но
    0.09
    Activations Density 0.181%

    No Known Activations