Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 122808
    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Area
    -0.06
    ปกครอง
    -0.06
    enie
    -0.06
     avenue
    -0.06
    degree
    -0.06
     ultimately
    -0.06
    <vector
    -0.06
     juego
    -0.06
    Lua
    -0.06
    .mobile
    -0.06
    POSITIVE LOGITS
     Disk
    0.07
    描
    0.06
    _equalTo
    0.06
     �
    0.06
     Yardım
    0.06
     TIMES
    0.06
     RGB
    0.06
     ط
    0.06
     wrongful
    0.06
    نسان
    0.06
    Activations Density 0.002%

    No Known Activations