© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2309
    Prev
    Next
    INDEX
    Explanations

    separators and sentence starts

    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
     à¸ģรà¸ģ
    -0.10
     retract
    -0.08
     gratis
    -0.08
    rim
    -0.08
    628
    -0.08
    492
    -0.07
    quared
    -0.07
    âĶĶ
    -0.07
     Bounty
    -0.07
    tte
    -0.07
    POSITIVE LOGITS
    âĢį
    0.10
    ifu
    0.09
    pollo
    0.09
     :/:
    0.09
    Touchable
    0.08
    ulumi
    0.08
    .Dictionary
    0.08
    pdev
    0.07
     Eigen
    0.07
    ä¸ĢçĤ¹
    0.07
    Activations Density 0.047%

    No Known Activations