© 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. 26587
    Prev
    Next
    INDEX
    Explanations

    input related context

    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
    ---</
    -0.09
    .VK
    -0.08
    ¶Į
    -0.08
    \Array
    -0.08
    SharedPointer
    -0.08
    ¦æĥħ
    -0.08
    printStats
    -0.08
     gratuites
    -0.08
    .Formatter
    -0.08
    ķãĤĵ
    -0.07
    POSITIVE LOGITS
    /input
    0.09
    /on
    0.08
     input
    0.07
    /by
    0.07
    [r
    0.07
     Rousse
    0.07
    -à¤ħ
    0.07
    aton
    0.06
    input
    0.06
     ------>
    0.06
    Activations Density 2.128%

    No Known Activations