© 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. 24074
    Prev
    Next
    INDEX
    Explanations

    out followed by common words or phrases

    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
    /s
    -0.10
     amen
    -0.09
     consenting
    -0.09
    RAR
    -0.09
     Ling
    -0.09
    ustomed
    -0.08
    h
    -0.08
    éĢł
    -0.08
    bole
    -0.08
     presum
    -0.08
    POSITIVE LOGITS
    ages
    0.17
    source
    0.17
    -of
    0.17
    lying
    0.15
    wards
    0.15
    ta
    0.15
    AGES
    0.14
    sid
    0.14
    ift
    0.13
    Standing
    0.13
    Activations Density 0.031%

    No Known Activations