© 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. 45118
    Prev
    Next
    INDEX
    Explanations

    the number, criteria, laws, types, intentions

    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
    ocommerce
    -0.09
    uddle
    -0.09
    ignon
    -0.09
     лÑĮ
    -0.09
    esson
    -0.08
     manner
    -0.08
    EditingController
    -0.08
    eyse
    -0.08
    ynchronously
    -0.08
    362
    -0.08
    POSITIVE LOGITS
    oretical
    0.14
    tas
    0.13
     sexes
    0.10
    tat
    0.10
    ore
    0.09
    fts
    0.09
    anzi
    0.09
    SES
    0.09
    ft
    0.09
    chn
    0.09
    Activations Density 0.211%

    No Known Activations