© 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. 33550
    Prev
    Next
    INDEX
    Explanations

    completes sentences or requests

    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
    adow
    -0.09
     Equip
    -0.09
    iyah
    -0.09
    _PUSHDATA
    -0.08
     Petty
    -0.08
     Xin
    -0.08
    abis
    -0.08
    ãĤĨ
    -0.08
    .sul
    -0.08
    achuset
    -0.08
    POSITIVE LOGITS
     unfinished
    0.17
     Completion
    0.15
     sentences
    0.14
     completion
    0.13
    unfinished
    0.13
     finishing
    0.12
     completes
    0.12
     completing
    0.12
    (completion
    0.12
    以ä¸ĭ
    0.11
    Activations Density 0.036%

    No Known Activations