© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7668
    Prev
    Next
    INDEX
    Explanations

    graphics rendering

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of off‐screen rendering operations—especially references to framebuffers, render targets, FBOs, and resolve/post‐processing steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bride
    -0.07
    	view
    -0.07
     Fro
    -0.07
    bm
    -0.06
    標
    -0.06
     учнів
    -0.06
    157
    -0.06
     Гер
    -0.06
    -tone
    -0.06
    asurer
    -0.06
    POSITIVE LOGITS
    Taken
    0.07
     framebuffer
    0.06
     solitary
    0.06
    Ads
    0.06
     advertiser
    0.06
     mailing
    0.06
     command
    0.06
    quirer
    0.06
     Then
    0.06
     additional
    0.06
    Activations Density 0.013%

    No Known Activations