© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2003
    Prev
    Next
    INDEX
    Explanations

    books, movies, music, media

    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
    lys
    -0.09
     Lantern
    -0.08
    ·æĸ°
    -0.08
     fx
    -0.08
     fle
    -0.08
     Pays
    -0.08
    abcdefghijklmnopqrstuvwxyz
    -0.08
    _deck
    -0.08
     decks
    -0.08
     Reb
    -0.08
    POSITIVE LOGITS
     censor
    0.19
     censorship
    0.19
    ALA
    0.17
     Fahrenheit
    0.15
     banned
    0.15
     AL
    0.14
     library
    0.14
    /Library
    0.13
    libraries
    0.12
     è¨Ģ
    0.12
    Activations Density 0.017%

    No Known Activations