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. 11-RESID-POST-AA
    6. 104274
    Prev
    Next
    INDEX
    Explanations

    as

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     эконом
    -0.07
     ][
    -0.06
    Greetings
    -0.06
    yii
    -0.06
    javax
    -0.06
    Japan
    -0.06
     Fresh
    -0.06
     Scrap
    -0.06
     Exped
    -0.06
     shortage
    -0.06
    POSITIVE LOGITS
     thẳng
    0.07
    ①
    0.06
     разом
    0.06
     sóng
    0.06
     IPCC
    0.06
     chỉ
    0.06
     الوط
    0.06
     dahi
    0.06
     instantaneous
    0.06
    指
    0.06
    Activations Density 0.013%

    No Known Activations