© 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. 59213
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    The neuron activates on direct second-person address, especially the word “you” (and related constructs) speaking to the reader.

    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
    fills
    -0.08
    .Accessible
    -0.07
    θούν
    -0.07
     二
    -0.07
    case
    -0.07
    _five
    -0.06
    _datasets
    -0.06
    .userData
    -0.06
     Worce
    -0.06
    _REPORT
    -0.06
    POSITIVE LOGITS
    طب
    0.07
    ีล
    0.07
     Agu
    0.06
     호텔
    0.06
    ements
    0.06
     tienes
    0.06
     hydr
    0.06
    oop
    0.06
     Kamp
    0.06
    iect
    0.06
    Activations Density 0.017%

    No Known Activations