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. 21286
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    ога
    -0.08
    package
    -0.07
     comprehension
    -0.07
     '=',
    -0.07
     Drugs
    -0.06
    _notifications
    -0.06
     eldest
    -0.06
     Personnel
    -0.06
    ип
    -0.06
    OAuth
    -0.06
    POSITIVE LOGITS
    蜘蛛
    0.06
    业务
    0.06
     декіль
    0.06
     نشده
    0.06
    /animations
    0.06
     بالاتر
    0.06
    овід
    0.06
    iov
    0.06
     Coleman
    0.05
    layın
    0.05
    Activations Density 0.272%

    No Known Activations