© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 34858
    Prev
    Next
    INDEX
    Explanations

    gerenciador de arquivos file explorer

    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
     gre
    -0.12
    rego
    -0.10
     greedy
    -0.10
    ç¿
    -0.09
     Toolbox
    -0.09
     cong
    -0.09
    gre
    -0.09
     congr
    -0.09
    fest
    -0.09
     Lara
    -0.09
    POSITIVE LOGITS
     explorer
    0.14
     finder
    0.14
     Finder
    0.14
     Explorer
    0.13
    Explorer
    0.13
    plorer
    0.13
     tree
    0.12
    Finder
    0.12
    filer
    0.12
     Midnight
    0.12
    Activations Density 0.114%

    No Known Activations