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. 104397
    Prev
    Next
    INDEX
    Explanations

    ReSharper

    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
     Tiffany
    -0.07
    ."',
    -0.06
    ozřejmě
    -0.06
     mutlaka
    -0.06
     Tire
    -0.06
    instanc
    -0.06
    cordova
    -0.06
    ้าต
    -0.06
     Paleo
    -0.06
     tkinter
    -0.06
    POSITIVE LOGITS
     revisions
    0.07
    sy
    0.07
     Lesson
    0.07
     enacted
    0.07
     lesson
    0.07
     widening
    0.06
    .backgroundColor
    0.06
     ReSharper
    0.06
    p
    0.06
    {-
    0.06
    Activations Density 0.001%

    No Known Activations