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. 21361
    Prev
    Next
    INDEX
    Explanations

    more

    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
     cellFor
    -0.08
     armored
    -0.07
     查询
    -0.07
     ıs
    -0.07
     squirrel
    -0.07
     όπου
    -0.06
     resilient
    -0.06
    _for
    -0.06
    [k
    -0.06
    (ptr
    -0.06
    POSITIVE LOGITS
     زیاد
    0.07
    του
    0.07
    -mouth
    0.06
    /table
    0.06
    
    0.06
    vit
    0.06
     releg
    0.06
     hete
    0.06
     Unauthorized
    0.06
     empt
    0.06
    Activations Density 0.046%

    No Known Activations