© 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. 24588
    Prev
    Next
    INDEX
    Explanations

    second place or order

    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
    ÌĨ
    -0.12
    Ìĥ
    -0.09
     اÙĦØ£ÙĪÙĦÙī
    -0.09
    uzzi
    -0.09
     tertiary
    -0.08
     اÙĦØ£ÙĪÙĦ
    -0.08
     scaleX
    -0.08
     -*-č\n
    -0.07
    egin
    -0.07
     numerator
    -0.07
    POSITIVE LOGITS
     second
    0.21
    âij¡
    0.20
     Second
    0.19
     اÙĦثاÙĨÙĬ
    0.19
    第äºĮ
    0.19
    äºĮ
    0.18
     第äºĮ
    0.17
    02
    0.17
     SECOND
    0.17
     II
    0.16
    Activations Density 0.203%

    No Known Activations