© 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. 34390
    Prev
    Next
    INDEX
    Explanations

    help and provide

    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
     dov
    -0.11
    iku
    -0.10
    neau
    -0.10
     Credit
    -0.10
    amber
    -0.10
     inde
    -0.09
     gang
    -0.09
     autom
    -0.09
    alie
    -0.09
     OSS
    -0.09
    POSITIVE LOGITS
     provide
    0.10
    HIR
    0.10
     hope
    0.10
     cung
    0.10
     answer
    0.10
     providing
    0.10
    æıIJä¾Ľ
    0.10
    å¸ĮæľĽ
    0.09
    hope
    0.09
     proporcion
    0.09
    Activations Density 0.076%

    No Known Activations