© 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. 59182
    Prev
    Next
    INDEX
    Explanations

    personnel

    np_max-act · gemini-2.0-flash

    This neuron activates on references to “personnel,” i.e. mentions of staff or workforce.

    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
    James
    -0.07
     James
    -0.06
    ,arg
    -0.06
    Experiment
    -0.06
     Does
    -0.06
    Jack
    -0.06
    ζό
    -0.06
     wants
    -0.06
    又
    -0.06
    が出
    -0.06
    POSITIVE LOGITS
     personnel
    0.16
     Personnel
    0.14
     endured
    0.08
    uli
    0.08
    norm
    0.08
     Manuel
    0.08
     personal
    0.08
     přítom
    0.08
    .UI
    0.07
    uly
    0.07
    Activations Density 0.005%

    No Known Activations