© 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. 13888
    Prev
    Next
    INDEX
    Explanations

    adding a delay, border, email, index, ratio

    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
    ment
    -0.10
    Disallow
    -0.09
    :::
    -0.09
    746
    -0.09
     Aux
    -0.08
     COVER
    -0.08
    ation
    -0.08
     exempt
    -0.08
    508
    -0.08
    izo
    -0.08
    POSITIVE LOGITS
     overall
    0.11
     Evet
    0.10
     (
    0.09
    ãĢĢï½
    0.09
     global
    0.09
     encount
    0.09
     seedu
    0.09
     suce
    0.09
     S
    0.09
     built
    0.08
    Activations Density 0.183%

    No Known Activations