© 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. 66425
    Prev
    Next
    INDEX
    Explanations

    -dev

    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
    ουργ
    -0.07
    (props
    -0.06
    **
    ↵
    -0.06
    .PNG
    -0.06
     �
    -0.06
    (actual
    -0.06
    _storage
    -0.06
    _extent
    -0.06
     müm
    -0.06
     مشاركة
    -0.06
    POSITIVE LOGITS
    讯
    0.08
     dank
    0.07
     Indies
    0.07
     مايو
    0.06
    ;,
    0.06
    941
    0.06
    -de
    0.06
     Madden
    0.06
    体育
    0.06
     live
    0.06
    Activations Density 0.002%

    No Known Activations