© 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. 18293
    Prev
    Next
    INDEX
    Explanations

    addition after in

    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
    ãģħ
    -0.10
    abad
    -0.09
     meanwhile
    -0.09
     across
    -0.08
     according
    -0.08
    andr
    -0.08
     Across
    -0.08
    eci
    -0.08
    otty
    -0.08
    /
    -0.08
    POSITIVE LOGITS
     addition
    0.49
    éĻ¤äºĨ
    0.45
     além
    0.41
     عÙĦاÙĪÙĩ
    0.41
     además
    0.41
     oltre
    0.40
    Besides
    0.38
     Besides
    0.37
     beyond
    0.36
     kromÄĽ
    0.36
    Activations Density 0.263%

    No Known Activations