© 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. 37884
    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_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
    Export
    -0.08
    izon
    -0.07
     Exchange
    -0.07
    Exchange
    -0.07
    ка
    -0.07
     compounds
    -0.06
    (H
    -0.06
    /K
    -0.06
     floral
    -0.06
     bank
    -0.06
    POSITIVE LOGITS
     bieten
    0.07
    тоф
    0.06
     earthqu
    0.06
     Pune
    0.06
    บบ
    0.06
    умент
    0.06
     bundan
    0.06
     Destructor
    0.06
    ">--}}↵
    0.06
    |)↵
    0.06
    Activations Density 0.051%

    No Known Activations