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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 31129
    Prev
    Next
    INDEX
    Explanations

    role models

    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
     spotting
    -0.06
    غراف
    -0.06
    .Tween
    -0.06
     Serializer
    -0.06
    println
    -0.06
    ApplicationContext
    -0.06
     تحميل
    -0.06
     نشر
    -0.06
     Listener
    -0.06
     под
    -0.06
    POSITIVE LOGITS
    .permissions
    0.07
     Limited
    0.07
     intra
    0.06
     manufacturing
    0.06
     roky
    0.06
    ,$
    0.06
     قرار
    0.06
     emerg
    0.06
    (reverse
    0.06
     Wolver
    0.06
    Activations Density 0.064%

    No Known Activations