© 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. 24810
    Prev
    Next
    INDEX
    Explanations

    still alive or present

    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
     ab
    -0.10
     Permanent
    -0.09
     Duy
    -0.09
    orthand
    -0.09
     Bik
    -0.08
     dw
    -0.08
    ãĢĢãĥ¾
    -0.08
     unus
    -0.08
    ume
    -0.08
    checker
    -0.08
    POSITIVE LOGITS
     alive
    0.79
    alive
    0.61
     Alive
    0.59
     live
    0.56
    Alive
    0.55
     жив
    0.51
     living
    0.50
     lived
    0.50
    æ´»
    0.49
     زÙĨدÙĩ
    0.47
    Activations Density 0.120%

    No Known Activations