© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38084
    Prev
    Next
    INDEX
    Explanations

    hand signs and gestures

    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
     footsteps
    -0.10
     kneeling
    -0.10
     knees
    -0.09
     ankles
    -0.09
     breath
    -0.09
    asz
    -0.09
    ypi
    -0.09
    iler
    -0.09
    entes
    -0.08
    803
    -0.08
    POSITIVE LOGITS
     gesture
    0.38
     gest
    0.38
     gestures
    0.34
     Gesture
    0.32
    gest
    0.30
     Gest
    0.28
    gesture
    0.27
     wave
    0.26
     raised
    0.25
    GEST
    0.24
    Activations Density 0.074%

    No Known Activations