© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109728
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects the boilerplate publication notice of a court opinion (the “Published by New York State Law Reporting Bureau pursuant to Judiciary Law § 431” line).

    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
    剑
    -0.07
    旧
    -0.07
     христи
    -0.07
    ificaciones
    -0.07
     Kumar
    -0.07
    (clock
    -0.07
    іти
    -0.07
    Wars
    -0.06
    詩
    -0.06
    -pencil
    -0.06
    POSITIVE LOGITS
     SATA
    0.06
    Hosting
    0.06
    _checked
    0.06
     {_
    0.06
    /up
    0.06
     hangi
    0.06
    (handle
    0.06
     doGet
    0.06
     Gaga
    0.06
    			    
    0.05
    Activations Density 0.001%

    No Known Activations