© 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. 69017
    Prev
    Next
    INDEX
    Explanations

    terminal commands

    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
     lovers
    -0.06
    inge
    -0.06
    hos
    -0.06
     yahoo
    -0.06
     fundamental
    -0.06
    cer
    -0.06
    asury
    -0.06
     electronic
    -0.06
    ynchronized
    -0.05
    '):↵
    -0.05
    POSITIVE LOGITS
    .getDeclared
    0.06
     Franc
    0.06
     Scarlett
    0.06
     IDEA
    0.06
     aylık
    0.06
     معماری
    0.06
    etSocketAddress
    0.06
     існу
    0.06
     сох
    0.06
     몰
    0.06
    Activations Density 0.068%

    No Known Activations