© 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. 18591
    Prev
    Next
    INDEX
    Explanations

    code/logs

    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
     Vz
    -0.06
     compos
    -0.06
     mientras
    -0.06
     Kom
    -0.06
    (global
    -0.06
     MOST
    -0.06
    	Register
    -0.06
    하였
    -0.06
    impse
    -0.06
     jihadist
    -0.05
    POSITIVE LOGITS
     žen
    0.07
    ็็
    0.06
    nicos
    0.06
    기업
    0.06
    ungle
    0.06
    ��
    0.06
    .blog
    0.06
    ensions
    0.06
    Attachments
    0.06
    tractive
    0.06
    Activations Density 0.048%

    No Known Activations