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. 80649
    Prev
    Next
    INDEX
    Explanations

    (WebDriver

    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
    )L
    -0.07
    clientId
    -0.06
     checkbox
    -0.06
    znám
    -0.06
    กระท
    -0.06
    asbourg
    -0.06
    .Split
    -0.06
     ATP
    -0.05
     intermediary
    -0.05
     Zak
    -0.05
    POSITIVE LOGITS
    _css
    0.07
    遇
    0.06
     เต
    0.06
     δε
    0.06
     TableName
    0.06
    彩票
    0.06
    FXML
    0.06
    ,type
    0.06
     rebels
    0.06
    _manage
    0.06
    Activations Density 0.000%

    No Known Activations