© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23631
    Prev
    Next
    INDEX
    Explanations

    there followed by be or have

    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
     tends
    -0.12
     tend
    -0.11
    orne
    -0.10
    ought
    -0.10
     Ard
    -0.10
    emic
    -0.09
    gh
    -0.09
     ​​
    -0.09
     ch
    -0.09
     tended
    -0.08
    POSITIVE LOGITS
    for
    0.10
    cwd
    0.09
     ØŃاج
    0.09
    apeutic
    0.09
    ceipt
    0.09
    afort
    0.09
    atz
    0.09
    by
    0.09
    urb
    0.09
    erosis
    0.09
    Activations Density 0.037%

    No Known Activations