© 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. 13766
    Prev
    Next
    INDEX
    Explanations

    field property member attribute

    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
    à¸ĵà¸ij
    -0.10
     function
    -0.10
     unions
    -0.09
    Porno
    -0.09
    iffe
    -0.09
     functions
    -0.09
    #af
    -0.08
    pu
    -0.08
    494
    -0.08
     roots
    -0.08
    POSITIVE LOGITS
     properties
    0.25
     property
    0.23
     attributes
    0.22
    å±ŀæĢ§
    0.21
     member
    0.21
     attribute
    0.20
     members
    0.20
     instance
    0.19
     Properties
    0.18
    properties
    0.18
    Activations Density 0.064%

    No Known Activations