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. 80838
    Prev
    Next
    INDEX
    Explanations

    modern society and culture

    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
     progressives
    -0.07
    755
    -0.07
     approaches
    -0.06
     transcription
    -0.06
    学习
    -0.06
    定的
    -0.06
    رس
    -0.06
    usiness
    -0.06
    (ra
    -0.06
    rx
    -0.06
    POSITIVE LOGITS
     thanh
    0.07
    Estado
    0.06
     Affero
    0.06
    状態
    0.06
    CMD
    0.06
     serbest
    0.06
     errorMsg
    0.06
    异常
    0.06
     लक
    0.06
    iltere
    0.06
    Activations Density 0.063%

    No Known Activations