© 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. 9991
    Prev
    Next
    INDEX
    Explanations

    actions initiating or directing

    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
    alia
    -0.10
     Hod
    -0.09
     ÑĢÑı
    -0.09
    assi
    -0.09
    ewe
    -0.09
    umer
    -0.09
    ovÃŃ
    -0.09
    /Foundation
    -0.08
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
    Ïĥκ
    -0.08
    POSITIVE LOGITS
     forth
    0.12
    296
    0.09
    -in
    0.09
     shut
    0.09
     together
    0.09
    اء
    0.09
    -out
    0.09
    erator
    0.09
    ãĤĿ
    0.09
    led
    0.08
    Activations Density 0.111%

    No Known Activations