© 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. 56948
    Prev
    Next
    INDEX
    Explanations

    variety of ingredients

    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
     Moor
    -0.12
     vinegar
    -0.11
     fruit
    -0.11
     marin
    -0.10
     Beef
    -0.10
    izz
    -0.10
    adele
    -0.10
     Fruit
    -0.10
    PropTypes
    -0.09
     beef
    -0.09
    POSITIVE LOGITS
     cream
    0.25
     Cream
    0.20
    cream
    0.18
     rou
    0.18
     creamy
    0.16
    Cream
    0.16
     heavy
    0.16
     milk
    0.16
     Alfred
    0.14
     Milk
    0.14
    Activations Density 0.024%

    No Known Activations