© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38286
    Prev
    Next
    INDEX
    Explanations

    cut and following words

    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
    Negative Logits
    hind
    -0.11
    oice
    -0.10
    íĮ
    -0.09
    eur
    -0.09
    izzo
    -0.09
    apolis
    -0.09
    esco
    -0.09
    edBy
    -0.09
    oled
    -0.09
    eum
    -0.09
    POSITIVE LOGITS
    aneous
    0.24
    ters
    0.23
    throat
    0.22
    tings
    0.21
    ting
    0.20
    tle
    0.18
    scenes
    0.18
    omers
    0.18
    cut
    0.17
    eness
    0.17
    Activations Density 0.026%

    No Known Activations