© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 128091
    Prev
    Next
    INDEX
    Explanations

    Mary

    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
    .Iterator
    -0.09
    [G
    -0.08
     سي
    -0.08
    建設
    -0.07
     synchron
    -0.07
     canopy
    -0.07
    兼
    -0.07
    CCR
    -0.07
     preempt
    -0.07
     Vapor
    -0.07
    POSITIVE LOGITS
     Mary
    0.12
    Mary
    0.10
     mary
    0.08
     mapped
    0.07
    areth
    0.07
     Anna
    0.07
     mats
    0.06
    표
    0.06
     приклад
    0.06
    ews
    0.06
    Activations Density 0.010%

    No Known Activations