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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 43253
    Prev
    Next
    INDEX
    Explanations

    delegate

    np_max-act · gemini-2.0-flash

    The neuron activates on lines declaring or listing delegate/dataSource protocols (e.g. “UITableViewDelegate”, “UICollectionViewDataSource”) in code.

    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
     KBS
    -0.06
     sculpt
    -0.06
    !***
    -0.06
    ::.
    -0.06
    vtColor
    -0.06
     TW
    -0.06
    _lstm
    -0.06
    .avatar
    -0.06
     System
    -0.06
    Tbl
    -0.05
    POSITIVE LOGITS
    ace
    0.07
     isp
    0.07
    ertility
    0.07
    「
    0.06
    ACE
    0.06
     Чи
    0.06
     "+↵
    0.06
     grease
    0.06
    edin
    0.06
    grep
    0.06
    Activations Density 0.002%

    No Known Activations