© 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. 17422
    Prev
    Next
    INDEX
    Explanations

    action before

    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
    //{{
    -0.10
     Urb
    -0.09
    ays
    -0.08
    -ahead
    -0.08
    .hasNext
    -0.08
    urus
    -0.08
     sonraki
    -0.08
    bor
    -0.08
     preceded
    -0.08
    preced
    -0.07
    POSITIVE LOGITS
     before
    0.80
    before
    0.64
     Before
    0.55
    Before
    0.52
     trÆ°á»Ľc
    0.50
     antes
    0.50
    _before
    0.47
     ÙĤبÙĦ
    0.45
    -before
    0.42
    \tbefore
    0.39
    Activations Density 0.031%

    No Known Activations