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. 80721
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
     selective
    -0.07
     selectively
    -0.07
     recurs
    -0.07
     Nevada
    -0.06
    .UTC
    -0.06
    лата
    -0.06
    PX
    -0.06
    .writeValue
    -0.06
    Than
    -0.06
     deliber
    -0.06
    POSITIVE LOGITS
     GHz
    0.07
     hlad
    0.07
     빈
    0.06
     başarılı
    0.06
    ướng
    0.06
    aaaa
    0.06
    
    0.06
     •
    0.06
    _ud
    0.06
     имя
    0.06
    Activations Density 0.871%

    No Known Activations