© 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. 25132
    Prev
    Next
    INDEX
    Explanations

    1500-2000 words

    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
    Stencil
    -0.09
    veal
    -0.09
    abus
    -0.08
    пÑĸд
    -0.08
    bak
    -0.08
    aga
    -0.08
    ffer
    -0.08
    isu
    -0.08
    ered
    -0.08
    dG
    -0.08
    POSITIVE LOGITS
     Mesh
    0.12
     mesh
    0.11
     Jarvis
    0.09
     times
    0.09
     Gab
    0.09
    ADR
    0.09
     molecular
    0.09
    бÑĢÑı
    0.08
     Chatt
    0.08
    .Matrix
    0.08
    Activations Density 0.023%

    No Known Activations