© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 45346
    Prev
    Next
    INDEX
    Explanations

    math and science, pulling, competitiveness, shape, ball, lunch, cyber attacks, garden, piano

    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
    EGIN
    -0.08
    upert
    -0.08
    eo
    -0.08
    941
    -0.08
     ...\n\n\n\n
    -0.08
    มาย
    -0.08
    째
    -0.08
    озем
    -0.08
    typeid
    -0.08
     udp
    -0.08
    POSITIVE LOGITS
    PHA
    0.08
    à¹īà¹ī
    0.08
    ¨
    0.08
     {?}
    0.08
    Ë
    0.08
    _verbose
    0.08
     Ish
    0.07
     [.
    0.07
    âĢĮ
    0.07
    owing
    0.07
    Activations Density 0.239%

    No Known Activations