© 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. 33647
    Prev
    Next
    INDEX
    Explanations

    Sports tournaments/events

    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
    (Connection
    -0.08
     shown
    -0.07
    ond
    -0.06
    oksen
    -0.06
    ValueCollection
    -0.06
     اندازه
    -0.06
     hare
    -0.06
    ydı
    -0.06
    距離
    -0.06
    UT
    -0.06
    POSITIVE LOGITS
    accounts
    0.07
     enable
    0.06
     RESOURCE
    0.06
    413
    0.06
     Dallas
    0.06
     Ukra
    0.06
     Required
    0.06
     biến
    0.06
    reed
    0.06
    classification
    0.06
    Activations Density 0.019%

    No Known Activations