© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38244
    Prev
    Next
    INDEX
    Explanations

    appeal or resonate

    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
    Negative Logits
     Hancock
    -0.10
    awk
    -0.09
    anga
    -0.09
     McInt
    -0.09
    ADM
    -0.09
    ãģ£
    -0.09
    asn
    -0.09
     aroused
    -0.08
    ze
    -0.08
     unm
    -0.08
    POSITIVE LOGITS
     appeal
    0.47
     Appeal
    0.39
     appeals
    0.35
     appealed
    0.29
     Appeals
    0.28
    appe
    0.28
    Appe
    0.27
     appealing
    0.26
     reson
    0.25
     appe
    0.19
    Activations Density 0.173%

    No Known Activations