© 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. 4685
    Prev
    Next
    INDEX
    Explanations

    importance and interest

    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
    ä¸Ģç§į
    -0.12
    undos
    -0.11
     remainder
    -0.10
    425
    -0.10
    ä¸ĢäºĽ
    -0.09
     dimin
    -0.09
    agua
    -0.09
    ä¸ĢåĢĭ
    -0.09
    æķ¬
    -0.09
    ä¸ĢçĤ¹
    -0.09
    POSITIVE LOGITS
     interest
    0.47
     importance
    0.38
     Interest
    0.37
    Interest
    0.34
     concern
    0.33
    interest
    0.32
     significance
    0.31
     note
    0.30
     Importance
    0.30
    -interest
    0.26
    Activations Density 0.085%

    No Known Activations