© 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. 29763
    Prev
    Next
    INDEX
    Explanations

    district

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of administrative subdivisions—especially the word “district” (and its local equivalents like “amphoe,” “tambon,” etc.).

    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
     Pieces
    -0.07
    inds
    -0.06
     bikes
    -0.06
     shade
    -0.06
     Wo
    -0.06
    am
    -0.06
    .comboBox
    -0.06
     Cros
    -0.06
     Kir
    -0.06
     некоторые
    -0.06
    POSITIVE LOGITS
     Keeper
    0.08
    [M
    0.07
    heiten
    0.07
     novelty
    0.06
    apy
    0.06
     ल
    0.06
    .MenuItem
    0.06
    -educated
    0.06
    ности
    0.06
     departing
    0.06
    Activations Density 0.010%

    No Known Activations