© 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. 43264
    Prev
    Next
    INDEX
    Explanations

    magic and wizards

    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
     rake
    -0.10
    天åłĤ
    -0.09
    鬼
    -0.09
    _HARD
    -0.09
    647
    -0.09
    indow
    -0.09
     aliens
    -0.09
    antine
    -0.09
     Ellison
    -0.09
    Boss
    -0.09
    POSITIVE LOGITS
     magic
    0.21
     sor
    0.21
     Magic
    0.19
     nec
    0.18
     spell
    0.18
     mag
    0.17
     spells
    0.17
    magic
    0.17
    Magic
    0.16
    éŃĶæ³ķ
    0.16
    Activations Density 0.121%

    No Known Activations