© 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. 18131
    Prev
    Next
    INDEX
    Explanations

    bedrooms, bathrooms, kitchen, views

    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
     housing
    -0.11
     Wohnung
    -0.11
    æĪ¿å±ĭ
    -0.11
     accommodation
    -0.10
    housing
    -0.10
    æĪ¿
    -0.10
    å±ĭ
    -0.10
     Housing
    -0.10
     Apartments
    -0.10
    aty
    -0.10
    POSITIVE LOGITS
     Jac
    0.15
     separate
    0.14
     parking
    0.14
     views
    0.14
    Views
    0.14
     Juliet
    0.13
     Views
    0.13
     maid
    0.12
     Parking
    0.12
     master
    0.12
    Activations Density 0.078%

    No Known Activations