© 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. 7-RESID-POST-AA
    6. 40999
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     другие
    -0.07
     کش
    -0.07
     系
    -0.07
     (),↵
    -0.07
    _CONNECTION
    -0.07
    申
    -0.07
    Array
    -0.06
    /'↵
    -0.06
    甘
    -0.06
     흔
    -0.06
    POSITIVE LOGITS
    erving
    0.07
     Kathryn
    0.07
     felon
    0.06
     πέ
    0.06
    achable
    0.06
    qui
    0.06
     impover
    0.06
    Qty
    0.06
     neon
    0.06
    oblin
    0.06
    Activations Density 0.042%

    No Known Activations