© 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. 3508
    Prev
    Next
    INDEX
    Explanations

    its activity; produces Galantamine; predominant allergen

    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
     Engl
    -0.09
    resses
    -0.09
    ï¾ī
    -0.09
     Hipp
    -0.09
     Expanded
    -0.09
    rador
    -0.09
     proteins
    -0.09
    éri
    -0.09
     egg
    -0.09
     Rounded
    -0.09
    POSITIVE LOGITS
     Northern
    0.18
    Northern
    0.15
     post
    0.12
     autor
    0.12
    autor
    0.11
     expression
    0.11
     antis
    0.11
     rat
    0.10
     hybrid
    0.10
     probe
    0.10
    Activations Density 0.027%

    No Known Activations