© 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. 23536
    Prev
    Next
    INDEX
    Explanations

    function documentation

    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
     Inherits
    -0.16
    Defines
    -0.13
     Executes
    -0.11
     Resets
    -0.11
    Specifies
    -0.11
     Validates
    -0.11
     Specifies
    -0.10
     Defines
    -0.10
     Parses
    -0.10
     Redistributions
    -0.10
    POSITIVE LOGITS
    doc
    0.13
     This
    0.12
     doc
    0.11
    description
    0.11
     desc
    0.11
    DOC
    0.10
     description
    0.10
     DOC
    0.10
    Doc
    0.10
    æĹ
    0.10
    Activations Density 0.042%

    No Known Activations