© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    witchcraft and magic

    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
    GuidId
    -0.10
    rvine
    -0.09
    èģĸ
    -0.09
    妻
    -0.09
    ormsg
    -0.09
     dÅĻÃŃ
    -0.09
    edor
    -0.09
     gezocht
    -0.09
    aurus
    -0.08
    CADE
    -0.08
    POSITIVE LOGITS
     witch
    0.25
     hex
    0.24
    witch
    0.23
     witches
    0.23
     Witch
    0.23
     HEX
    0.21
     Salem
    0.21
     Hex
    0.21
    Hex
    0.20
    hex
    0.19
    Activations Density 0.086%

    No Known Activations