© 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. 23-RESID-POST-AA
    11. 62931
    Prev
    Next
    INDEX
    Explanations

    fasc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    	Returns
    -0.07
    Lee
    -0.06
    _dump
    -0.06
     прежде
    -0.06
     nodeName
    -0.06
    .tex
    -0.06
    ンダ
    -0.06
    oard
    -0.06
    ücret
    -0.06
    兄
    -0.06
    POSITIVE LOGITS
     tenure
    0.06
    Ř
    0.06
    ЛИ
    0.06
     agreed
    0.06
    лит
    0.06
     gra
    0.06
    ionic
    0.06
     pantalla
    0.06
    acci
    0.06
    ButtonItem
    0.06
    Activations Density 0.002%

    No Known Activations