© 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. 13825
    Prev
    Next
    INDEX
    Explanations

    movements

    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
     sext
    -0.10
    Collapsed
    -0.10
    inality
    -0.09
     vis
    -0.09
    -ie
    -0.09
     pÅĻen
    -0.09
     Machines
    -0.09
     Cros
    -0.09
     ìĨIJ
    -0.09
    indsight
    -0.08
    POSITIVE LOGITS
     moving
    0.16
     move
    0.16
     movement
    0.15
    -moving
    0.14
    移åĬ¨
    0.12
    éļı
    0.12
     Moving
    0.12
     pohyb
    0.12
     Respond
    0.12
    moving
    0.12
    Activations Density 0.139%

    No Known Activations