© 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. 74677
    Prev
    Next
    INDEX
    Explanations

    Topics being discussed

    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
     utilizando
    -0.07
     viên
    -0.06
     عليك
    -0.06
    licer
    -0.06
    modify
    -0.06
    "Why
    -0.06
     Guild
    -0.06
     butterfly
    -0.06
     Paşa
    -0.06
     sacr
    -0.06
    POSITIVE LOGITS
    .OrdinalIgnoreCase
    0.07
    logic
    0.06
     인정
    0.06
    Regex
    0.06
    LookAndFeel
    0.06
     satu
    0.06
     Vec
    0.06
    แท
    0.06
    	table
    0.06
     choking
    0.06
    Activations Density 0.003%

    No Known Activations