© 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. 124404
    Prev
    Next
    INDEX
    Explanations

    garden

    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
    meeting
    -0.06
    YLON
    -0.06
    眼
    -0.06
    uyor
    -0.06
    出し
    -0.06
    opathy
    -0.06
    éd
    -0.06
     olds
    -0.06
     PVC
    -0.06
     tests
    -0.06
    POSITIVE LOGITS
    عکس
    0.07
    ."[
    0.06
    �
    0.06
    "'↵
    0.06
     Baghdad
    0.06
    .News
    0.06
     impover
    0.06
     intimately
    0.06
     jpg
    0.06
     cuộc
    0.06
    Activations Density 0.017%

    No Known Activations