© 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. 33644
    Prev
    Next
    INDEX
    Explanations

    vector followed by bt, of, robot, or 2

    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
    kola
    -0.11
     ãĢĢ ãĢĢ
    -0.10
    oltage
    -0.09
     ãĢĢ ãĢĢ ãĢĢ
    -0.09
    olis
    -0.09
    ãĢĢV
    -0.09
     ith
    -0.09
    acz
    -0.09
    scr
    -0.08
    ivar
    -0.08
    POSITIVE LOGITS
    ial
    0.27
    ized
    0.22
    ization
    0.17
    ize
    0.17
    izer
    0.16
    ised
    0.16
    izing
    0.16
    izable
    0.16
    ially
    0.15
    izes
    0.15
    Activations Density 0.017%

    No Known Activations