© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 94913
    Prev
    Next
    INDEX
    Explanations

    :

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以下
    -0.07
     Saint
    -0.07
    Saint
    -0.07
     trên
    -0.06
    >Contact
    -0.06
    งของ
    -0.06
    دان
    -0.06
    Sit
    -0.06
     مایل
    -0.06
     Bhar
    -0.06
    POSITIVE LOGITS
     Registers
    0.07
    OFFSET
    0.06
    .tm
    0.06
    门
    0.06
    nell
    0.06
     improper
    0.06
     vec
    0.06
    quist
    0.06
    wy
    0.06
     Disorders
    0.06
    Activations Density 0.038%

    No Known Activations