© 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. 128289
    Prev
    Next
    INDEX
    Explanations

    Art

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific style modifiers—especially references to artists, artistic mediums, and other style-related keywords.

    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
    ONES
    -0.06
    вроп
    -0.06
    BindView
    -0.06
    backup
    -0.06
    CellValue
    -0.06
     buffer
    -0.06
     EFF
    -0.06
    도로
    -0.06
     mpg
    -0.06
    romosome
    -0.06
    POSITIVE LOGITS
     tạm
    0.07
     jenis
    0.06
     Recently
    0.06
    .Buffered
    0.06
     Analysis
    0.06
    Marks
    0.06
    .QueryString
    0.06
    /File
    0.06
     statistical
    0.06
     SALE
    0.06
    Activations Density 0.006%

    No Known Activations