© 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. 27740
    Prev
    Next
    INDEX
    Explanations

    early language models predicting

    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
    .xhtml
    -0.10
     Bayesian
    -0.09
    ãĥ¼ãĥģ
    -0.08
    aupt
    -0.08
    ensibly
    -0.08
     pornos
    -0.08
    orraine
    -0.08
    owie
    -0.08
    æģ
    -0.08
    StdString
    -0.08
    POSITIVE LOGITS
     traditional
    0.21
     classical
    0.18
    traditional
    0.18
     approaches
    0.17
    Traditional
    0.17
     Traditional
    0.16
     rule
    0.16
     classic
    0.14
    classic
    0.14
    rule
    0.13
    Activations Density 0.183%

    No Known Activations