© 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. 18800
    Prev
    Next
    INDEX
    Explanations

    2

    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
    (Database
    -0.07
    ضم
    -0.07
    _Final
    -0.06
    纪
    -0.06
    したら
    -0.06
     measure
    -0.06
    _Post
    -0.06
    862
    -0.06
     пор
    -0.06
    pain
    -0.06
    POSITIVE LOGITS
     mouseClicked
    0.07
    daq
    0.07
    ",$
    0.06
    urdy
    0.06
    _teacher
    0.06
    yscale
    0.06
    rsa
    0.06
     Taco
    0.06
    -hot
    0.06
    TreeView
    0.06
    Activations Density 0.001%

    No Known Activations