© 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. 17578
    Prev
    Next
    INDEX
    Explanations

    harmless piece of virus or bacteria

    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
     Antib
    -0.12
     infected
    -0.12
     antim
    -0.12
    avit
    -0.12
     Infect
    -0.11
     inoc
    -0.11
     antib
    -0.10
     cavern
    -0.10
     infection
    -0.09
    avez
    -0.09
    POSITIVE LOGITS
     live
    0.18
     attenu
    0.17
     Killed
    0.16
    live
    0.16
     Live
    0.15
    -live
    0.15
     alum
    0.15
     killed
    0.15
    Live
    0.15
     Hib
    0.14
    Activations Density 0.046%

    No Known Activations