© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24921
    Prev
    Next
    INDEX
    Explanations

    limitless interpretations of truth

    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
    gid
    -0.09
     tad
    -0.09
    PLY
    -0.09
    _ABC
    -0.08
     assim
    -0.08
     Bowman
    -0.08
     dna
    -0.08
    nbr
    -0.08
    urement
    -0.08
     forte
    -0.08
    POSITIVE LOGITS
     necessarily
    0.09
    ibold
    0.09
     Script
    0.09
     Kral
    0.09
     Cron
    0.08
     sped
    0.08
    emonic
    0.08
    905
    0.08
     scrub
    0.08
     understand
    0.08
    Activations Density 0.031%

    No Known Activations