© 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. 8225
    Prev
    Next
    INDEX
    Explanations

    verbs followed by nouns or noun phrases

    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
     newest
    -0.11
    617
    -0.10
    æľĢæĸ°
    -0.09
    /from
    -0.09
     ELSE
    -0.09
    ausal
    -0.09
    615
    -0.09
     thr
    -0.08
    /to
    -0.08
     Robbins
    -0.08
    POSITIVE LOGITS
     various
    0.25
     certain
    0.18
     Various
    0.16
     additional
    0.16
    åIJĦç§į
    0.14
     appropriate
    0.14
    Various
    0.14
     çeÅŁitli
    0.14
     several
    0.14
     further
    0.14
    Activations Density 0.126%

    No Known Activations