© 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. 40894
    Prev
    Next
    INDEX
    Explanations

    electric, mobile, virtual, public, industrial, voice

    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
     Hatch
    -0.11
    ±Ð¾ÑĤ
    -0.10
    ividad
    -0.09
    ystack
    -0.09
    noÅĽÄĩ
    -0.09
    emez
    -0.09
    åĻ
    -0.08
    ÑģÑĮко
    -0.08
    ãĥ¼ãĥŃ
    -0.08
    ographically
    -0.08
    POSITIVE LOGITS
    -related
    0.09
    iale
    0.09
     âĶĤ
    0.09
    amentals
    0.08
     quá»ijc
    0.08
    amental
    0.08
    iero
    0.08
    âĢİ
    0.08
     Riv
    0.08
    uais
    0.08
    Activations Density 0.120%

    No Known Activations