© 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. 54567
    Prev
    Next
    INDEX
    Explanations

    renewal or extension

    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
    erdem
    -0.09
    ething
    -0.09
    acom
    -0.09
    eko
    -0.09
     Reyes
    -0.08
    plen
    -0.08
     Repair
    -0.08
    æģ¯
    -0.08
     resilient
    -0.08
    ToPoint
    -0.08
    POSITIVE LOGITS
     renewal
    0.69
     renew
    0.69
     Renew
    0.59
     renewed
    0.49
    Ren
    0.38
    ç»Ń
    0.37
     renewable
    0.35
     extension
    0.33
    çºĮ
    0.29
     extensions
    0.29
    Activations Density 0.078%

    No Known Activations