© 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. 27184
    Prev
    Next
    INDEX
    Explanations

    defeat deficiency defect defendant

    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
    ingham
    -0.10
    íħIJ
    -0.10
    bero
    -0.10
    ullo
    -0.10
    holes
    -0.10
    иÑİ
    -0.10
    hole
    -0.09
    .IsNull
    -0.09
    ãģĻãģIJ
    -0.09
    ãģĻãģ¹ãģ¦
    -0.09
    POSITIVE LOGITS
    ively
    0.17
    iveness
    0.16
    ives
    0.14
    atur
    0.12
    ive
    0.10
    /null
    0.10
    atted
    0.10
    uous
    0.10
    rous
    0.10
    initely
    0.10
    Activations Density 0.027%

    No Known Activations