© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33257
    Prev
    Next
    INDEX
    Explanations

    models, variables, dataset

    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
    <|begin_of_text|>
    -0.10
    ÑĤÑĶ
    -0.08
    ellan
    -0.08
     nuest
    -0.08
    ëħķ
    -0.08
    apur
    -0.08
    okane
    -0.08
    .viewDidLoad
    -0.07
    ersistent
    -0.07
    .mybatis
    -0.07
    POSITIVE LOGITS
     %[
    0.10
     original
    0.09
     others
    0.09
     vice
    0.09
     ones
    0.09
    #ac
    0.08
     existing
    0.08
     previous
    0.08
     #'
    0.08
    ____
    0.08
    Activations Density 0.121%

    No Known Activations