© 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. 15-RESID-POST-AA
    11. 45634
    Prev
    Next
    INDEX
    Explanations

    code and quotes

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mount
    -0.07
     Av
    -0.07
     фак
    -0.07
     Mits
    -0.07
     initiation
    -0.07
     lud
    -0.06
    .For
    -0.06
     axial
    -0.06
     feedback
    -0.06
     <->
    -0.06
    POSITIVE LOGITS
     Newly
    0.07
    
    0.07
     jeans
    0.06
    loyment
    0.06
     resultList
    0.06
     लगभग
    0.06
    ReadWrite
    0.06
     jspb
    0.06
    aryl
    0.06
    CTSTR
    0.06
    Activations Density 0.029%

    No Known Activations