© 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. 47138
    Prev
    Next
    INDEX
    Explanations

    underlying factors, causes, or structure

    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
     Huntington
    -0.10
    pret
    -0.09
     darüber
    -0.09
     kal
    -0.09
     ============================================================================\n
    -0.09
    yte
    -0.09
    rypton
    -0.09
    aldi
    -0.09
    elerik
    -0.08
    571
    -0.08
    POSITIVE LOGITS
    /internal
    0.11
     Haut
    0.10
    /down
    0.10
    /Main
    0.10
    /Internal
    0.09
     workings
    0.09
    719
    0.09
     Beau
    0.09
    anela
    0.09
     heartbeat
    0.08
    Activations Density 0.260%

    No Known Activations