© 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. 21619
    Prev
    Next
    INDEX
    Explanations

    AI and drones potential

    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
     became
    -0.10
     ÑģÑĤало
    -0.08
     helf
    -0.08
     become
    -0.08
    дÑı
    -0.08
    :::|
    -0.08
    omap
    -0.08
    ecast
    -0.08
     becomes
    -0.08
    ÙĬÙĤ
    -0.08
    POSITIVE LOGITS
     potentially
    0.30
     potential
    0.27
     could
    0.27
     Potential
    0.24
     promise
    0.23
     Could
    0.23
    could
    0.22
    Could
    0.21
     promises
    0.21
     поÑĤен
    0.21
    Activations Density 0.074%

    No Known Activations