© 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. 38815
    Prev
    Next
    INDEX
    Explanations

    operation performed

    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
    zelf
    -0.11
     Bray
    -0.11
    owing
    -0.10
    edException
    -0.09
    EventManager
    -0.09
    unning
    -0.09
    cly
    -0.08
    -Cs
    -0.08
    pedia
    -0.08
    /std
    -0.08
    POSITIVE LOGITS
    ally
    0.25
    als
    0.18
     performed
    0.15
    ALLY
    0.14
    nal
    0.14
    (Operation
    0.13
    reation
    0.13
    符
    0.13
    nelle
    0.12
    Performed
    0.12
    Activations Density 0.034%

    No Known Activations