© 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. 24098
    Prev
    Next
    INDEX
    Explanations

    èĬĤ followed by èĥ½

    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
    borough
    -0.09
    isoft
    -0.09
    ring
    -0.09
    ivalent
    -0.09
    pun
    -0.09
    ingt
    -0.09
    ssf
    -0.09
    orta
    -0.09
    urgeon
    -0.09
     odense
    -0.09
    POSITIVE LOGITS
    ëĮĢë¡ľ
    0.11
    нÑĮ
    0.10
    Ñİ
    0.10
    pcf
    0.09
     muster
    0.09
    Wer
    0.09
    ictions
    0.08
    helper
    0.08
    ãģ¡
    0.08
     faded
    0.08
    Activations Density 0.020%

    No Known Activations