© 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. 63049
    Prev
    Next
    INDEX
    Explanations

    ar

    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
    aload
    -0.07
    �
    -0.06
    imid
    -0.06
    *log
    -0.06
     πολ
    -0.06
    actly
    -0.06
     condem
    -0.06
    _su
    -0.06
    achment
    -0.06
     Renderer
    -0.06
    POSITIVE LOGITS
    عان
    0.07
    jspx
    0.07
    Ｒ
    0.07
     конечно
    0.07
    ier
    0.07
     ฟร
    0.07
     nüfus
    0.07
    anos
    0.06
     AssetImage
    0.06
    andro
    0.06
    Activations Density 15.565%

    No Known Activations