© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109740
    Prev
    Next
    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens related to directly addressing or “addressing” the reader/audience.

    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
    记录
    -0.07
     veri
    -0.07
     договору
    -0.06
     TEntity
    -0.06
    -demo
    -0.06
    ์พ
    -0.06
     chipset
    -0.06
    ubbo
    -0.06
     qint
    -0.06
     synerg
    -0.06
    POSITIVE LOGITS
     addresses
    0.08
     addressed
    0.08
     directed
    0.08
    _address
    0.07
     addressing
    0.07
     Address
    0.07
     address
    0.07
    Direct
    0.07
     чолов
    0.07
    Address
    0.07
    Activations Density 0.012%

    No Known Activations