© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34977
    Prev
    Next
    INDEX
    Explanations

    content types and 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
    iverz
    -0.09
    chter
    -0.09
    esser
    -0.09
    аÑĤÑĸ
    -0.08
    riel
    -0.08
    assis
    -0.08
    Ø´ÙĪ
    -0.08
     SUBSTITUTE
    -0.08
     Clarkson
    -0.08
    vlc
    -0.08
    POSITIVE LOGITS
     itself
    0.14
     samt
    0.10
     Mund
    0.10
     determines
    0.09
    uben
    0.09
    antee
    0.09
     sowie
    0.08
    以åıĬ
    0.08
    elm
    0.08
    IMP
    0.08
    Activations Density 0.195%

    No Known Activations