© 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. 15-RESID-POST-AA
    6. 2493
    Prev
    Next
    INDEX
    Explanations

    Yeah

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    walls
    -0.06
     configured
    -0.06
    _UPDATED
    -0.06
    ��이
    -0.06
    letcher
    -0.06
    original
    -0.06
     Icon
    -0.06
     facet
    -0.06
    .Branch
    -0.06
     financing
    -0.06
    POSITIVE LOGITS
     militia
    0.07
     hus
    0.07
     ري
    0.07
    Φ
    0.07
     ilg
    0.06
    оло
    0.06
     متعدد
    0.06
     intercepted
    0.06
    BW
    0.06
     Č
    0.06
    Activations Density 0.023%

    No Known Activations