© 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. 7-RESID-POST-AA
    11. 64943
    Prev
    Next
    INDEX
    Explanations

    restaurant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     decode
    -0.07
     Imaging
    -0.07
    imulation
    -0.07
    gage
    -0.06
     tagging
    -0.06
    Map
    -0.06
     ----------------------------------------------------------------------------------------------------------------
    -0.06
     chaining
    -0.06
    .clone
    -0.06
     gains
    -0.06
    POSITIVE LOGITS
     restaurant
    0.16
     restaurants
    0.13
     Restaurant
    0.11
     Restaurants
    0.10
    restaurant
    0.10
    Restaurant
    0.09
    aurants
    0.09
    restaurants
    0.09
     restau
    0.08
    .restaurant
    0.08
    Activations Density 0.008%

    No Known Activations