© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7039
    Prev
    Next
    INDEX
    Explanations

    __)

    np_max-act · gemini-2.0-flash

    This neuron detects the line where a Flask app is created (the “app = Flask(__name__)” statement).

    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
    .Line
    -0.06
    野
    -0.06
     Intercept
    -0.06
    Resolver
    -0.06
     آیا
    -0.06
    思考
    -0.06
     ;;
    -0.06
    .Keys
    -0.06
    ason
    -0.06
    振
    -0.06
    POSITIVE LOGITS
    ční
    0.06
    ización
    0.06
    >We
    0.06
    .getExternal
    0.06
    láv
    0.06
     Làm
    0.06
     SOCKET
    0.06
    =<?=
    0.06
     işlem
    0.06
    blah
    0.06
    Activations Density 0.002%

    No Known Activations