© 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. 22513
    Prev
    Next
    INDEX
    Explanations

    X words or prefixes

    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
    xyz
    -0.12
     XYZ
    -0.12
    XYZ
    -0.11
    xy
    -0.11
    _xyz
    -0.11
     xyz
    -0.09
     XY
    -0.09
     stitch
    -0.09
     yAxis
    -0.09
     Thy
    -0.09
    POSITIVE LOGITS
     X
    0.20
    =X
    0.16
    GetX
    0.15
    \tX
    0.14
     x
    0.14
    >X
    0.13
     getX
    0.13
    *X
    0.12
    ,X
    0.12
    :X
    0.12
    Activations Density 0.159%

    No Known Activations