© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 37769
    Prev
    Next
    INDEX
    Explanations

    per night stays

    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
    'gc
    -0.13
     daytime
    -0.10
     tard
    -0.09
    istro
    -0.09
    otto
    -0.09
    ottom
    -0.09
     Noon
    -0.08
     ãĢĢ 
    -0.08
     Lounge
    -0.08
    itters
    -0.08
    POSITIVE LOGITS
     stay
    0.43
     stays
    0.33
     Stay
    0.33
     stayed
    0.32
     staying
    0.32
    stay
    0.32
     overnight
    0.31
    Stay
    0.31
    overn
    0.30
     night
    0.30
    Activations Density 0.077%

    No Known Activations