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. 54401
    Prev
    Next
    INDEX
    Explanations

    Code parameters

    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
    depend
    -0.07
    -E
    -0.06
    anko
    -0.06
    тие
    -0.06
     SCRIPT
    -0.06
     trendy
    -0.06
     Мак
    -0.06
     E
    -0.06
     Рос
    -0.06
    categoryId
    -0.06
    POSITIVE LOGITS
     uint
    0.06
     )
    ↵
    0.06
     نوع
    0.06
    าต
    0.06
    :@"%@",
    0.06
     iterate
    0.06
     NSMutableArray
    0.06
     btnCancel
    0.06
    ieri
    0.06
     isFirst
    0.06
    Activations Density 0.004%

    No Known Activations