© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42123
    Prev
    Next
    INDEX
    Explanations

    continues, lasts, duration

    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
    illis
    -0.09
     longer
    -0.09
    оÑĤв
    -0.09
     Longer
    -0.09
     surviving
    -0.09
     Tender
    -0.09
     поба
    -0.09
    gue
    -0.09
    彦
    -0.09
    strand
    -0.09
    POSITIVE LOGITS
     stay
    0.24
     lasted
    0.23
     stayed
    0.23
     remained
    0.22
     lasts
    0.21
    æĮģç»Ń
    0.20
     continued
    0.19
    Stay
    0.19
     continue
    0.19
     stays
    0.19
    Activations Density 0.118%

    No Known Activations