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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43446
    Prev
    Next
    INDEX
    Explanations

    predicting continuous outcomes

    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
    uxtap
    -0.11
     Rooney
    -0.09
    ToDevice
    -0.09
    é®
    -0.09
    UGHT
    -0.09
     rowNum
    -0.08
     آذ
    -0.08
    hai
    -0.08
    ktop
    -0.08
    edback
    -0.08
    POSITIVE LOGITS
     continuous
    0.39
    continuous
    0.34
     Continuous
    0.33
    Continuous
    0.33
    _continuous
    0.22
     quantitative
    0.22
     contin
    0.22
     interval
    0.21
     continuously
    0.19
    è¿ŀ
    0.18
    Activations Density 0.114%

    No Known Activations