© 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. 11-RESID-POST-AA
    6. 27946
    Prev
    Next
    INDEX
    Explanations

    Breaking down or analysis

    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
     Century
    -0.07
    اة
    -0.06
     Ath
    -0.06
     Ctrl
    -0.06
    /Web
    -0.06
    -educated
    -0.06
    份
    -0.06
     bakery
    -0.06
     devote
    -0.06
     awk
    -0.06
    POSITIVE LOGITS
     priv
    0.07
     детей
    0.07
    .println
    0.07
    148
    0.07
    фер
    0.06
    込み
    0.06
     عکس
    0.06
    ModelCreating
    0.06
     temper
    0.06
     Subscriber
    0.06
    Activations Density 0.028%

    No Known Activations