© 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. 56437
    Prev
    Next
    INDEX
    Explanations

    game-changer, loss, difficult

    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
    æĥĬ
    -0.10
     impress
    -0.09
     surprise
    -0.09
    neo
    -0.09
    rema
    -0.09
    åİ
    -0.09
    é©ļ
    -0.09
    eware
    -0.09
    ADS
    -0.09
    شاÙĩ
    -0.09
    POSITIVE LOGITS
     prospect
    0.17
     liber
    0.12
    tractive
    0.12
     appeal
    0.12
     prospects
    0.11
    Appe
    0.11
     appealing
    0.11
     scenario
    0.11
    appe
    0.11
     excited
    0.10
    Activations Density 0.038%

    No Known Activations