© 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. 37741
    Prev
    Next
    INDEX
    Explanations

    LEO Pharma

    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
    WSC
    -0.09
    essler
    -0.09
    eren
    -0.09
    icl
    -0.09
    llum
    -0.08
     Dive
    -0.08
    edException
    -0.08
    íħIJ
    -0.08
     Roose
    -0.08
     inconvenience
    -0.08
    POSITIVE LOGITS
    .GPIO
    0.13
    ãĥ
    0.09
    plib
    0.09
    åĨ
    0.09
    iosper
    0.08
    hill
    0.08
    uddy
    0.08
     Walt
    0.08
    _IOC
    0.08
    ordion
    0.08
    Activations Density 0.199%

    No Known Activations