© 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. 10623
    Prev
    Next
    INDEX
    Explanations

    clarity and understandability

    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
     wording
    -0.10
     slightly
    -0.09
     Phrase
    -0.09
    reen
    -0.09
    oplay
    -0.09
     fert
    -0.08
     ÑĤÑĢÑĥб
    -0.08
     prob
    -0.08
    ckt
    -0.08
    oola
    -0.08
    POSITIVE LOGITS
     spell
    0.16
     proof
    0.16
     leg
    0.15
     Spell
    0.14
    spell
    0.13
    SPELL
    0.12
     Arial
    0.12
     font
    0.12
     Font
    0.12
     grammar
    0.12
    Activations Density 0.120%

    No Known Activations