© 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. 59433
    Prev
    Next
    INDEX
    Explanations

    ell

    np_max-act · gemini-2.0-flash

    The neuron detects references to multi‐well plate assay formats (e.g. “96‐well” or “microplate”).

    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
     Zw
    -0.06
    atham
    -0.06
     railway
    -0.06
     فراهم
    -0.06
     steroid
    -0.06
     Factor
    -0.06
     حول
    -0.06
    řej
    -0.06
     утвержд
    -0.06
    :y
    -0.06
    POSITIVE LOGITS
    吗
    0.07
    unar
    0.06
     dread
    0.06
     BuzzFeed
    0.06
    .emit
    0.06
     görmek
    0.06
     Exodus
    0.06
    .grid
    0.06
    _note
    0.06
    bru
    0.06
    Activations Density 0.001%

    No Known Activations