© 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. 23213
    Prev
    Next
    INDEX
    Explanations

    Founding dates

    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
    ToDelete
    -0.06
    (android
    -0.06
     жен
    -0.06
    �
    -0.06
    etes
    -0.06
    	Gtk
    -0.06
    ,无
    -0.06
     prost
    -0.06
    tp
    -0.06
    -google
    -0.06
    POSITIVE LOGITS
     minut
    0.07
    ’dan
    0.07
     sayılı
    0.07
     Belediyesi
    0.07
     пас
    0.07
    ível
    0.07
     restrain
    0.07
    вано
    0.07
    :+
    0.06
    จำนวน
    0.06
    Activations Density 0.047%

    No Known Activations