© 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. 26741
    Prev
    Next
    INDEX
    Explanations

    generative adversarial networks

    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
    MBER
    -0.09
    _Lean
    -0.09
     supra
    -0.09
    _compiler
    -0.09
    urope
    -0.08
    asher
    -0.08
     Volk
    -0.08
     graphene
    -0.08
     kn
    -0.08
     resil
    -0.08
    POSITIVE LOGITS
     gener
    0.31
     Gener
    0.30
    Gener
    0.25
    GAN
    0.21
    gener
    0.19
    _gener
    0.19
     advers
    0.18
     uns
    0.18
     GENER
    0.18
     géné
    0.18
    Activations Density 0.108%

    No Known Activations