© 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. 23084
    Prev
    Next
    INDEX
    Explanations

    legal/sentencing guidelines

    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
    .KeyCode
    -0.07
    Edition
    -0.06
     Mercer
    -0.06
    .toastr
    -0.06
     avid
    -0.06
     Hubbard
    -0.06
    .base
    -0.06
     Serif
    -0.06
    orro
    -0.06
     뜻
    -0.06
    POSITIVE LOGITS
     porta
    0.07
     plethora
    0.07
     Adresse
    0.06
     eman
    0.06
    .Symbol
    0.06
    ΑΜ
    0.06
     Functor
    0.06
    ><!--
    0.06
    報
    0.06
     telefono
    0.06
    Activations Density 0.006%

    No Known Activations