© 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. 58510
    Prev
    Next
    INDEX
    Explanations

    house/housing/shelter

    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
     Cottage
    -0.10
    ัส
    -0.10
     Domestic
    -0.10
     boasted
    -0.09
    .Helper
    -0.09
     Heidi
    -0.08
    mpp
    -0.08
     Fortress
    -0.08
    Mocks
    -0.08
     Herrera
    -0.08
    POSITIVE LOGITS
     host
    0.43
     housing
    0.42
     hosting
    0.40
     hosts
    0.36
     houses
    0.34
    Hosting
    0.33
     house
    0.32
    housing
    0.32
    host
    0.30
     Hosting
    0.30
    Activations Density 0.174%

    No Known Activations