© 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. 63104
    Prev
    Next
    INDEX
    Explanations

    describes which

    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
     constit
    -0.09
    fit
    -0.09
    932
    -0.09
    ogo
    -0.09
    quis
    -0.09
     synthes
    -0.08
    atsu
    -0.08
     ÏĢÏīÏĤ
    -0.08
    /
    -0.08
     furn
    -0.08
    POSITIVE LOGITS
     ÏĢοÏħ
    0.25
     whose
    0.24
     which
    0.21
     اÙĦتÙĬ
    0.19
     who
    0.19
     اÙĦØ°ÙĬ
    0.19
     Ú©Ùĩ
    0.19
     yang
    0.19
    whose
    0.18
    which
    0.17
    Activations Density 0.215%

    No Known Activations