© 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. 51757
    Prev
    Next
    INDEX
    Explanations

    changes from, he would

    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
     with
    -0.15
     avec
    -0.12
     damit
    -0.11
     vỼi
    -0.10
    \twith
    -0.10
     dengan
    -0.10
    ittel
    -0.10
    iram
    -0.09
     Cres
    -0.09
    ono
    -0.09
    POSITIVE LOGITS
     vengeance
    0.15
    .assertRaises
    0.14
     ÙĪÙħع
    0.14
    HasForeignKey
    0.13
    è¡
    0.11
     flourish
    0.10
    olding
    0.10
     regard
    0.10
     impunity
    0.10
     Mercer
    0.10
    Activations Density 0.321%

    No Known Activations