© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 45494
    Prev
    Next
    INDEX
    Explanations

    say "exit" words

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     matriz
    -0.07
     Cloth
    -0.06
     hình
    -0.06
    {
    ↵
    ↵
    -0.06
    Soup
    -0.06
     wealth
    -0.06
     Depression
    -0.06
     southwest
    -0.06
     seus
    -0.06
     Jefferson
    -0.06
    POSITIVE LOGITS
    (avg
    0.07
    ematic
    0.07
    ्वत
    0.06
    celed
    0.06
    nbsp
    0.06
    _tbl
    0.06
    ĞI
    0.06
    ์ม
    0.06
    €↵
    0.06
    έν
    0.06
    Activations Density 0.035%

    No Known Activations