Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 54228
    Prev
    Next
    INDEX
    Explanations

    div

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     language
    -0.08
     conductor
    -0.07
     Language
    -0.07
    IALOG
    -0.07
     Patient
    -0.07
     lipstick
    -0.07
    Identity
    -0.07
     retire
    -0.06
     Eggs
    -0.06
    selectors
    -0.06
    POSITIVE LOGITS
    ин
    0.07
     Pirates
    0.06
    ी,
    0.06
              
    0.06
    -div
    0.06
    /div
    0.06
    font
    0.06
    ‌گذ
    0.06
    (sprite
    0.06
    §Ã
    0.06
    Activations Density 0.012%

    No Known Activations