© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33474
    Prev
    Next
    INDEX
    Explanations

    office chairs, gaming chairs, rocking chairs

    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
     bedding
    -0.10
    lain
    -0.10
    crawl
    -0.10
     Champagne
    -0.10
    agle
    -0.09
    OAD
    -0.09
     è£
    -0.09
    ird
    -0.09
    INCLUDED
    -0.09
     Champ
    -0.08
    POSITIVE LOGITS
     chair
    0.55
     Chair
    0.46
     chairs
    0.45
    æ¤ħ
    0.45
    chair
    0.38
     Chairs
    0.36
    Chair
    0.35
    -chair
    0.33
     seat
    0.28
     ghế
    0.24
    Activations Density 0.060%

    No Known Activations