© 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. 22629
    Prev
    Next
    INDEX
    Explanations

    document introductions and sections

    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
     Publications
    -0.11
     Paragraph
    -0.11
    Paragraph
    -0.10
     publications
    -0.10
    æĬ±
    -0.10
     Homepage
    -0.10
     Lines
    -0.10
     article
    -0.10
    稿
    -0.10
    PEG
    -0.09
    POSITIVE LOGITS
     Fore
    0.24
     Pref
    0.23
     fore
    0.22
     Ded
    0.21
     dedication
    0.21
    Pref
    0.21
    Fore
    0.19
     pref
    0.18
    pref
    0.18
     Ack
    0.16
    Activations Density 0.093%

    No Known Activations