© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24390
    Prev
    Next
    INDEX
    Explanations

    quickly and, had always/set, grab/tackle

    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
    ihil
    -0.10
     penetr
    -0.09
     phá
    -0.09
    çīĩ
    -0.09
     squeez
    -0.09
     sustained
    -0.09
     discrim
    -0.09
    ddy
    -0.08
    æĵ¦
    -0.08
    Destroy
    -0.08
    POSITIVE LOGITS
     grab
    0.17
     amb
    0.15
     grabbed
    0.14
    grab
    0.14
    Grab
    0.14
     lung
    0.13
     grabs
    0.13
     Grab
    0.13
     corner
    0.13
     tackle
    0.13
    Activations Density 0.070%

    No Known Activations