© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59449
    Prev
    Next
    INDEX
    Explanations

    Romeo and Juliet

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized proper nouns, especially titles of plays/musicals and their main characters.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     belt
    -0.07
     microbial
    -0.07
    .quiz
    -0.07
     (@
    -0.06
    	panel
    -0.06
    PAL
    -0.06
     blanc
    -0.06
    .forRoot
    -0.06
     Μ
    -0.06
    &page
    -0.06
    POSITIVE LOGITS
     ><?
    0.07
     тех
    0.06
    .copy
    0.06
    >;↵
    0.06
    0.06
    _pll
    0.06
     spraw
    0.06
    ONT
    0.06
     окт
    0.06
    matched
    0.06
    Activations Density 0.002%

    No Known Activations