© 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. 231
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
     inches
    -0.21
     miles
    -0.19
     mile
    -0.19
     inch
    -0.17
     Miles
    -0.17
     yards
    -0.16
     feet
    -0.15
     yard
    -0.15
     gallon
    -0.14
    -mile
    -0.14
    POSITIVE LOGITS
    kg
    0.15
     kg
    0.14
    100
    0.13
    150
    0.13
    120
    0.12
    180
    0.12
    250
    0.12
    80
    0.12
     kilograms
    0.11
    kil
    0.11
    Activations Density 0.092%

    No Known Activations