© 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. 3773
    Prev
    Next
    INDEX
    Explanations

    calculating motion or direction

    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
    egend
    -0.11
     sha
    -0.10
     perm
    -0.09
    <::
    -0.09
    è½®
    -0.09
    Ascending
    -0.09
     bif
    -0.09
     bath
    -0.08
     Cros
    -0.08
     æĺ
    -0.08
    POSITIVE LOGITS
     movement
    0.28
     Movement
    0.22
     move
    0.21
     Move
    0.19
    Movement
    0.18
    movement
    0.18
     дви
    0.16
    .move
    0.16
     movimiento
    0.16
    è¿IJåĬ¨
    0.16
    Activations Density 0.092%

    No Known Activations