© 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. 37585
    Prev
    Next
    INDEX
    Explanations

    number of digits

    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
    oop
    -0.11
    lest
    -0.11
    spring
    -0.10
    yers
    -0.10
    OLT
    -0.09
    leigh
    -0.09
    «ĺ
    -0.09
    leo
    -0.09
    ERT
    -0.09
    ulate
    -0.09
    POSITIVE LOGITS
    als
    0.18
    ized
    0.16
    ally
    0.15
    ALS
    0.12
    álnÃŃ
    0.11
    ised
    0.11
    icult
    0.11
    rary
    0.11
    iation
    0.11
    ization
    0.10
    Activations Density 0.024%

    No Known Activations