© 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. 42146
    Prev
    Next
    INDEX
    Explanations

    higher, lower quantities

    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
    ابت
    -0.09
    buzz
    -0.09
    conciliation
    -0.09
    /pdf
    -0.09
    ãĥªãĤ«
    -0.08
    Networking
    -0.08
    ullet
    -0.08
    kov
    -0.08
    Poster
    -0.08
     ere
    -0.08
    POSITIVE LOGITS
     higher
    0.22
     low
    0.20
    ä½İ
    0.17
     high
    0.17
    higher
    0.17
    -low
    0.16
    low
    0.15
    é«ĺãģĦ
    0.15
     lower
    0.15
     Low
    0.15
    Activations Density 0.084%

    No Known Activations