© 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. 16242
    Prev
    Next
    INDEX
    Explanations

    one of, organization for, change-over, installation

    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
     approx
    -0.10
    lag
    -0.10
    aken
    -0.09
     rem
    -0.09
     lil
    -0.09
     redundancy
    -0.09
     Nic
    -0.09
     Spotlight
    -0.09
     Lik
    -0.09
     +-
    -0.08
    POSITIVE LOGITS
    gage
    0.10
     Wel
    0.10
    Legend
    0.10
     conv
    0.09
    Schedulers
    0.09
    elas
    0.09
     Kel
    0.09
     Legend
    0.09
     mole
    0.09
    xac
    0.09
    Activations Density 0.006%

    No Known Activations