© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 54588
    Prev
    Next
    INDEX
    Explanations

    explains consequences or capabilities

    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
    ī´
    -0.12
     pare
    -0.11
    ï¾IJ
    -0.10
    atron
    -0.10
    apol
    -0.09
     reportedly
    -0.09
    coni
    -0.09
     ÙħعÙĦ
    -0.09
     obviously
    -0.09
     seems
    -0.09
    POSITIVE LOGITS
     potentially
    0.13
     effectively
    0.11
     likely
    0.10
    azio
    0.10
    likely
    0.10
    oris
    0.10
     slugg
    0.10
     probably
    0.09
     nejen
    0.09
    ãģĭãģª
    0.09
    Activations Density 0.084%

    No Known Activations