© 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. 41406
    Prev
    Next
    INDEX
    Explanations

    Personal messages

    np_max-act · gemini-2.0-flash

    This neuron fires on polite or formal request/invitation language—phrases like “would be greatly appreciated,” “please,” “invite you,” and similar courteous expressions.

    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
    سان
    -0.08
    лава
    -0.08
     RECORD
    -0.07
    ượng
    -0.07
     dando
    -0.07
    áv
    -0.07
    .cv
    -0.07
     BUFF
    -0.06
    Contin
    -0.06
    Logger
    -0.06
    POSITIVE LOGITS
     anarchists
    0.06
     payer
    0.06
     levy
    0.06
    testCase
    0.06
    ชม
    0.05
    tips
    0.05
     targets
    0.05
     Practice
    0.05
     سبک
    0.05
     recall
    0.05
    Activations Density 0.032%

    No Known Activations