© 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. 14913
    Prev
    Next
    INDEX
    Explanations

    house, home, room

    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
    noinspection
    -0.11
    ÂĢÂĢ
    -0.10
    ecycle
    -0.09
    éº
    -0.09
    Spy
    -0.09
    avicon
    -0.09
    ¿ÃĤ
    -0.09
    ä¸ŃåѦ
    -0.08
     ÑĢай
    -0.08
    oader
    -0.08
    POSITIVE LOGITS
     house
    0.25
     homes
    0.14
     premise
    0.14
     building
    0.14
     houses
    0.14
    house
    0.13
     room
    0.13
     premises
    0.13
     place
    0.13
     office
    0.12
    Activations Density 0.133%

    No Known Activations