© 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. 35212
    Prev
    Next
    INDEX
    Explanations

    methods, facilities, providers, goals

    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
    :\n\n\n\n\n\n
    -0.09
    :\n\n\n\n
    -0.09
     Below
    -0.08
     :\n\n\n\n
    -0.08
    //*[
    -0.08
    ][/
    -0.07
    ulin
    -0.07
    ardo
    -0.07
    [url
    -0.07
     below
    -0.07
    POSITIVE LOGITS
    @nate
    0.10
     respectively
    0.08
     bypass
    0.08
    astery
    0.08
     including
    0.07
    .Retrofit
    0.07
    /&
    0.07
    stav
    0.07
     or
    0.07
     linked
    0.07
    Activations Density 0.051%

    No Known Activations