© 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. 37607
    Prev
    Next
    INDEX
    Explanations

    contrast or exceptions

    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
    ï¼Į以åıĬ
    -0.12
    URLException
    -0.11
    AdapterManager
    -0.10
    ritt
    -0.10
    StringEncoding
    -0.09
    ookeeper
    -0.09
    DataExchange
    -0.09
    ´Ī
    -0.09
    .toObject
    -0.09
    ï¼Į便
    -0.09
    POSITIVE LOGITS
     but
    0.15
     BUT
    0.12
     nhÆ°ng
    0.11
     но
    0.11
     pero
    0.10
    elder
    0.10
    but
    0.10
    ä½Ĩ
    0.09
     nên
    0.09
    ights
    0.09
    Activations Density 0.239%

    No Known Activations