© 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. 62151
    Prev
    Next
    INDEX
    Explanations

    whenever, wherever

    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
     maybe
    -0.10
    igen
    -0.10
     Herm
    -0.09
     lẫn
    -0.09
     olmadan
    -0.09
    akah
    -0.09
    kah
    -0.09
     Harr
    -0.08
    ston
    -0.08
     поÑĪ
    -0.08
    POSITIVE LOGITS
     whenever
    0.60
     Whenever
    0.48
    Whenever
    0.46
    enever
    0.34
    å°½
    0.29
     wherever
    0.25
     unless
    0.22
     möglich
    0.21
    wh
    0.19
     cÃłng
    0.19
    Activations Density 0.181%

    No Known Activations