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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 111374
    Prev
    Next
    INDEX
    Explanations

    SEO, search engines

    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
     Java
    -0.07
    irling
    -0.06
    kus
    -0.06
     encoding
    -0.06
     Zus
    -0.06
    getUser
    -0.06
     Shack
    -0.06
    研
    -0.06
     tgt
    -0.06
     creek
    -0.06
    POSITIVE LOGITS
    ebb
    0.07
    874
    0.06
     adher
    0.06
    говор
    0.06
    .Large
    0.06
    .slice
    0.06
     celebrates
    0.06
    menuItem
    0.06
     oy
    0.06
     Approximately
    0.06
    Activations Density 0.031%

    No Known Activations