© 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. 12968
    Prev
    Next
    INDEX
    Explanations

    generator expression, set intersection, regular expression, left join

    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
    ngth
    -0.09
    -caption
    -0.09
    iators
    -0.09
    onn
    -0.09
     Shields
    -0.08
    gran
    -0.08
    bole
    -0.08
    ipeg
    -0.08
    /Gate
    -0.08
    naire
    -0.08
    POSITIVE LOGITS
    -style
    0.10
     statements
    0.09
    irq
    0.09
     trick
    0.09
    oins
    0.09
     sentinel
    0.09
     totalTime
    0.09
    ython
    0.09
    -based
    0.08
    710
    0.08
    Activations Density 0.270%

    No Known Activations