© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74849
    Prev
    Next
    INDEX
    Explanations

    code complexity

    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
    poi
    -0.06
     <->
    -0.06
     ní
    -0.06
     publications
    -0.06
    -hole
    -0.06
     efficiently
    -0.06
    Texto
    -0.06
    Ve
    -0.06
    阳城
    -0.06
     DL
    -0.05
    POSITIVE LOGITS
     imaginable
    0.06
    LogLevel
    0.06
     ав
    0.06
     Hóa
    0.06
    埃
    0.06
     других
    0.06
     multif
    0.06
     муницип
    0.06
    opper
    0.06
     행복
    0.06
    Activations Density 0.002%

    No Known Activations