© 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. 25459
    Prev
    Next
    INDEX
    Explanations

    reading a book, consistent schedule

    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
     breakfast
    -0.10
    ushima
    -0.10
     lunch
    -0.10
     noon
    -0.09
    TypeDef
    -0.09
     Breakfast
    -0.09
     Sunshine
    -0.09
     sunshine
    -0.09
     drum
    -0.09
    norm
    -0.09
    POSITIVE LOGITS
     dim
    0.15
     Cham
    0.14
     wind
    0.14
     cham
    0.13
     warm
    0.13
     reading
    0.13
     mel
    0.12
     Evening
    0.12
     relaxation
    0.11
     winding
    0.11
    Activations Density 0.022%

    No Known Activations