© 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. 57709
    Prev
    Next
    INDEX
    Explanations

    lead to consequence or description

    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
    ce
    -0.10
     anymore
    -0.10
     ongoing
    -0.10
    fe
    -0.09
     xong
    -0.09
    ow
    -0.09
    le
    -0.09
    adar
    -0.09
    od
    -0.09
     Rol
    -0.09
    POSITIVE LOGITS
    xba
    0.11
     unless
    0.11
     شدÙĨ
    0.11
     being
    0.10
    .Undef
    0.10
    ayet
    0.10
     kab
    0.09
    âī¡âī¡
    0.09
    icens
    0.09
     Kro
    0.09
    Activations Density 0.078%

    No Known Activations