© 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. 63776
    Prev
    Next
    INDEX
    Explanations

    in ascending order

    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
     sle
    -0.09
     funding
    -0.09
     peg
    -0.09
    .OrderByDescending
    -0.09
    æ´¥
    -0.09
     Funding
    -0.08
     aba
    -0.08
     clen
    -0.08
    οÏħλ
    -0.08
     drops
    -0.08
    POSITIVE LOGITS
     asc
    0.32
     ascending
    0.31
     Asc
    0.27
    asc
    0.25
     increasing
    0.24
    åįĩ
    0.23
     ASC
    0.23
     ascend
    0.23
    æĺĩ
    0.22
    ascending
    0.22
    Activations Density 0.060%

    No Known Activations