© 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. 19-RESID-POST-AA
    11. 83834
    Prev
    Next
    INDEX
    Explanations

    ="

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     coating
    -0.06
    Father
    -0.06
     slaughter
    -0.06
    =>"
    -0.06
    Cert
    -0.06
    �
    -0.06
     řid
    -0.06
     asserting
    -0.06
     Tên
    -0.06
     advocating
    -0.06
    POSITIVE LOGITS
    мат
    0.07
    ocoa
    0.06
     darn
    0.06
     Bà
    0.06
    communications
    0.06
    リカ
    0.06
     QMainWindow
    0.06
    EUR
    0.06
     dostate
    0.06
    ERVICE
    0.06
    Activations Density 0.003%

    No Known Activations