© 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. 30434
    Prev
    Next
    INDEX
    Explanations

    verbs followed by their purpose or effect

    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
     itself
    -0.21
     its
    -0.13
    Its
    -0.10
    /is
    -0.10
    è¿Ļç§į
    -0.09
     Its
    -0.09
     коÑĤоÑĢое
    -0.09
    çļĦä¸Ģ个
    -0.09
     INCIDENTAL
    -0.09
    ascal
    -0.09
    POSITIVE LOGITS
     themselves
    0.28
     respectively
    0.27
     respective
    0.17
     together
    0.15
    åĪĨåĪ«
    0.14
     varying
    0.13
     thems
    0.13
     either
    0.12
     ÑģооÑĤвеÑĤ
    0.12
     sıras
    0.12
    Activations Density 0.165%

    No Known Activations