© 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. 31320
    Prev
    Next
    INDEX
    Explanations

    volumes, monitors, lights, clouds, statues

    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
    iel
    -0.10
    389
    -0.09
     itself
    -0.09
    vant
    -0.09
    kla
    -0.09
    appable
    -0.08
    vale
    -0.08
     Gib
    -0.08
    oproject
    -0.08
     gr
    -0.08
    POSITIVE LOGITS
     gal
    0.11
    มาà¸ģมาย
    0.10
    ills
    0.09
    erk
    0.09
     refr
    0.09
    åIJĦ
    0.08
    gal
    0.08
    ::-
    0.08
     Zot
    0.08
     sway
    0.08
    Activations Density 0.107%

    No Known Activations