© 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. 127060
    Prev
    Next
    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash

    This neuron detects direct second-person address, activating on tokens like “you,” “your,” and references to the human interlocutor.

    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
    报道
    -0.07
     airline
    -0.07
    uraa
    -0.06
     اتاق
    -0.06
     cow
    -0.06
     fon
    -0.06
    جاد
    -0.06
     contacto
    -0.06
    agascar
    -0.06
    dio
    -0.06
    POSITIVE LOGITS
     wrestlers
    0.06
     буд
    0.06
     Purch
    0.06
     Sovere
    0.06
     خصوص
    0.06
     Emoji
    0.06
    .cc
    0.06
    .ADMIN
    0.06
    Mui
    0.06
    ้ง
    0.06
    Activations Density 0.002%

    No Known Activations