© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24184
    Prev
    Next
    INDEX
    Explanations

    successful

    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
     consecutive
    -0.10
     Diss
    -0.09
    UnderTest
    -0.09
    IDI
    -0.09
    Exited
    -0.08
     SUBSTITUTE
    -0.08
     inher
    -0.08
    .gdx
    -0.08
    ForRow
    -0.08
    :.:
    -0.08
    POSITIVE LOGITS
     successful
    0.83
    æĪIJåĬŁ
    0.75
     Successful
    0.69
     successfully
    0.68
    successful
    0.65
     ÑĥÑģпеÑĪ
    0.62
    Successful
    0.59
     ìĦ±ê³µ
    0.55
     succeed
    0.55
     success
    0.55
    Activations Density 0.241%

    No Known Activations