© 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. 16522
    Prev
    Next
    INDEX
    Explanations

    move with arrow keys

    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
    Marshal
    -0.10
     OTA
    -0.10
     Cros
    -0.09
     Mori
    -0.09
     Morrow
    -0.09
     Miles
    -0.08
    Pin
    -0.08
     rele
    -0.08
     relief
    -0.08
    inh
    -0.08
    POSITIVE LOGITS
     movement
    0.21
     move
    0.16
     controls
    0.16
     direction
    0.16
     WAS
    0.16
    æĸ¹åIJij
    0.16
     arrow
    0.16
     Movement
    0.15
     Direction
    0.15
     Left
    0.14
    Activations Density 0.070%

    No Known Activations