© 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. 91385
    Prev
    Next
    INDEX
    Explanations

    celebrities

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of notable people’s names (celebrities, politicians, and other proper-name entities).

    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
     priest
    -0.07
     банк
    -0.07
     frustr
    -0.07
    ovi
    -0.07
     finals
    -0.06
     베스트
    -0.06
    στή
    -0.06
     initiative
    -0.06
    ブリ
    -0.06
    遺
    -0.06
    POSITIVE LOGITS
    .ReadKey
    0.07
    .getenv
    0.07
    ▏
    0.07
    .printf
    0.06
    .Down
    0.06
    gles
    0.06
    .Filters
    0.06
    .getAction
    0.06
     vaping
    0.06
    .setStyleSheet
    0.06
    Activations Density 0.035%

    No Known Activations