© 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. 64613
    Prev
    Next
    INDEX
    Explanations

    filled with

    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
    æĶ¾åľ¨
    -0.11
     Fischer
    -0.09
     worn
    -0.09
    Bru
    -0.09
     Tam
    -0.08
     haul
    -0.08
    çķ
    -0.08
     Moon
    -0.08
    dej
    -0.08
     Subset
    -0.08
    POSITIVE LOGITS
     filled
    0.53
    filled
    0.40
    Filled
    0.39
     llen
    0.31
     full
    0.29
    _filled
    0.28
     contains
    0.27
    -filled
    0.27
     fill
    0.26
     contain
    0.26
    Activations Density 0.220%

    No Known Activations