© 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. 34397
    Prev
    Next
    INDEX
    Explanations

    start of string or character

    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
     Cush
    -0.11
     Toro
    -0.10
    eah
    -0.09
     Rush
    -0.09
    816
    -0.09
    inton
    -0.09
     Miracle
    -0.09
    FINITE
    -0.08
     cra
    -0.08
     buzz
    -0.08
    POSITIVE LOGITS
     Dit
    0.10
    addock
    0.09
    .utf
    0.09
    iddet
    0.09
     ëĭ¤ìļ´ë°Ľê¸°
    0.09
    createElement
    0.09
    orthand
    0.09
    itorio
    0.08
    ilogue
    0.08
     Mister
    0.08
    Activations Density 0.226%

    No Known Activations