© 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. 39687
    Prev
    Next
    INDEX
    Explanations

    AMD FX computer processors and Call of Duty games

    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
     Patreon
    -0.12
     macOS
    -0.11
     Fortnite
    -0.10
    Blockchain
    -0.10
     VR
    -0.10
     Brexit
    -0.10
     fint
    -0.09
     Trump
    -0.09
    199
    -0.09
     skl
    -0.09
    POSITIVE LOGITS
     Occupy
    0.25
     Fukushima
    0.20
     Obama
    0.20
    201
    0.19
     WikiLeaks
    0.19
     Kinect
    0.17
     Skyrim
    0.17
     iPad
    0.17
    Obama
    0.16
     Barack
    0.14
    Activations Density 0.070%

    No Known Activations