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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44412
    Prev
    Next
    INDEX
    Explanations

    potential growth self constructor memory

    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
    ____
    -0.09
     newcom
    -0.09
    428
    -0.08
    èĥ½å¤Ł
    -0.08
    629
    -0.08
    ìĭľìĺ¤
    -0.08
     FREE
    -0.08
     )\n\n\n\n\n\n\n\n
    -0.07
     Previous
    -0.07
     Onc
    -0.07
    POSITIVE LOGITS
    <?\n
    0.09
    langs
    0.09
    ázev
    0.09
    ASSERT
    0.09
    arih
    0.09
    abcdefghijkl
    0.08
    porno
    0.08
    à¸ŀวà¸ģ
    0.08
    --------------------------------------------------------------------------\n
    0.08
    atsapp
    0.08
    Activations Density 0.138%

    No Known Activations