© 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. 45373
    Prev
    Next
    INDEX
    Explanations

    that starts text fragments

    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
    apan
    -0.09
    oen
    -0.09
    ORED
    -0.08
    rey
    -0.08
    omb
    -0.08
    este
    -0.08
    (
    -0.08
     predecessor
    -0.08
    ween
    -0.08
    tap
    -0.08
    POSITIVE LOGITS
    éĤ£æł·
    0.18
     That
    0.18
     that
    0.17
    That
    0.16
    éĤ£
    0.16
     toho
    0.15
    that
    0.15
    Ø°ÙĦÙĥ
    0.14
     ÑĤого
    0.14
     éĤ£
    0.14
    Activations Density 0.035%

    No Known Activations