© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    specific names and concepts

    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
     STDCALL
    -0.09
     grátis
    -0.09
     geil
    -0.09
    OnUiThread
    -0.09
     DERP
    -0.09
    CJK
    -0.09
     salope
    -0.09
    .createClass
    -0.09
    \<^
    -0.08
    )__
    -0.08
    POSITIVE LOGITS
    (
    0.08
    1
    0.08
    ạn
    0.08
    allery
    0.08
    6
    0.08
     mouseClicked
    0.08
     '?'
    0.07
    iar
    0.07
    &#
    0.07
     Singer
    0.07
    Activations Density 0.485%

    No Known Activations