© 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. 45379
    Prev
    Next
    INDEX
    Explanations

    uction

    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
    Not in Any Lists

    No Comments

    Negative Logits
     herr
    -0.07
     المو
    -0.07
    erto
    -0.06
    Mas
    -0.06
     campaigned
    -0.06
     الزر
    -0.06
    ными
    -0.06
    stre
    -0.06
    RE
    -0.06
    村
    -0.06
    POSITIVE LOGITS
     abduction
    0.08
     Duc
    0.07
     induction
    0.07
    岳
    0.07
     JPEG
    0.07
    クション
    0.06
    :Add
    0.06
     Türk
    0.06
    ducted
    0.06
    .ff
    0.06
    Activations Density 0.008%

    No Known Activations