© 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. 21194
    Prev
    Next
    INDEX
    Explanations

    swinging sword actions

    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
     shooters
    -0.13
     needles
    -0.13
     dagger
    -0.12
     Knife
    -0.12
     needle
    -0.12
     Bullet
    -0.12
     Twe
    -0.12
     Dagger
    -0.12
     bullet
    -0.11
     knife
    -0.11
    POSITIVE LOGITS
     swing
    0.25
     Swing
    0.25
     swung
    0.23
    swing
    0.23
     swings
    0.23
     cle
    0.21
    .swing
    0.21
     ax
    0.19
     hacking
    0.19
     swinging
    0.18
    Activations Density 0.035%

    No Known Activations