© 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. 30292
    Prev
    Next
    INDEX
    Explanations

    Max or maximizing

    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
    eca
    -0.10
    uang
    -0.10
    este
    -0.09
    istica
    -0.09
    uja
    -0.09
    ught
    -0.09
    pered
    -0.08
    lass
    -0.08
    932
    -0.08
    iyon
    -0.08
    POSITIVE LOGITS
    ималÑĮ
    0.21
    IMUM
    0.19
    imum
    0.18
    illary
    0.18
    =max
    0.17
    imal
    0.16
    imize
    0.15
    (Max
    0.14
    illian
    0.14
    ilian
    0.14
    Activations Density 0.021%

    No Known Activations