© 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. 54236
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    The neuron is looking for Python code that uses the PIL (Pillow) Image API—importing Image, opening or creating images, and putting text onto them.

    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
    	users
    -0.07
     Contractors
    -0.07
    grp
    -0.07
     resume
    -0.07
    Roy
    -0.06
    ื้
    -0.06
     Ordering
    -0.06
    음
    -0.06
     ears
    -0.06
    呼
    -0.06
    POSITIVE LOGITS
    .tie
    0.07
    写真
    0.07
    âce
    0.06
     stranded
    0.06
    andid
    0.06
     winters
    0.06
     tech
    0.06
     ebony
    0.06
     Sanayi
    0.06
     gender
    0.06
    Activations Density 0.076%

    No Known Activations