© 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. 31767
    Prev
    Next
    INDEX
    Explanations

    explain code commentary

    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
    inding
    -0.09
    azo
    -0.09
    izon
    -0.09
     hei
    -0.09
    imeo
    -0.08
    indo
    -0.08
     Latter
    -0.08
     завиÑģим
    -0.08
    YPE
    -0.08
    ZO
    -0.08
    POSITIVE LOGITS
     explain
    0.16
     поÑıÑģ
    0.16
    帮åĬ©
    0.14
     documentation
    0.14
    説æĺİ
    0.14
     explaining
    0.14
     erklä
    0.14
     explanation
    0.14
     help
    0.14
     explains
    0.14
    Activations Density 0.132%

    No Known Activations