© 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. 19-RESID-POST-AA
    11. 108808
    Prev
    Next
    INDEX
    Explanations

    Personal pronouns and forms of "be"

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -se
    -0.07
    BX
    -0.06
    .In
    -0.06
    istické
    -0.06
     we
    -0.06
    ughters
    -0.06
    サイト
    -0.06
    /umd
    -0.06
    χε
    -0.06
    provide
    -0.06
    POSITIVE LOGITS
    ATTERN
    0.07
     STRICT
    0.07
     applicationContext
    0.07
    	GPIO
    0.06
     sniff
    0.06
    inium
    0.06
    GTK
    0.06
     tenants
    0.06
     bek
    0.06
     inconvenient
    0.06
    Activations Density 0.022%

    No Known Activations