© 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. 37136
    Prev
    Next
    INDEX
    Explanations

    weakness

    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
    ーツ
    -0.07
     UITableViewCell
    -0.07
     headers
    -0.07
    �
    -0.06
     Probably
    -0.06
    QObject
    -0.06
    vet
    -0.06
    =""↵
    -0.06
    思
    -0.06
    >xpath
    -0.06
    POSITIVE LOGITS
    Length
    0.06
     monthly
    0.06
     컨
    0.06
     सम
    0.06
     Οικο
    0.06
    Tambah
    0.06
     agenda
    0.06
    .simpleButton
    0.06
    -entity
    0.06
     사라
    0.06
    Activations Density 0.019%

    No Known Activations