© 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. 23510
    Prev
    Next
    INDEX
    Explanations

    orientation and upside down

    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
     Mans
    -0.11
     swinging
    -0.09
     Benson
    -0.09
     regress
    -0.09
     æ¸
    -0.09
     Kendall
    -0.09
    ika
    -0.09
    657
    -0.09
    ToLeft
    -0.09
     triang
    -0.09
    POSITIVE LOGITS
    Ups
    0.27
     upside
    0.24
     Ups
    0.22
     orient
    0.20
     orientation
    0.18
     inverted
    0.18
     Orientation
    0.18
     inversion
    0.17
    Orientation
    0.17
    orientation
    0.16
    Activations Density 0.094%

    No Known Activations