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. 80820
    Prev
    Next
    INDEX
    Explanations

    inclusion

    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
    [
    -0.07
    	signal
    -0.07
     pans
    -0.06
     Kata
    -0.06
    -density
    -0.06
    人
    -0.06
    .borrow
    -0.06
     노출
    -0.06
     outward
    -0.06
    //(
    -0.06
    POSITIVE LOGITS
     burger
    0.08
     Baba
    0.06
     Canberra
    0.06
    γε
    0.06
    richt
    0.06
     何
    0.06
    ょ
    0.06
     UICollectionViewCell
    0.06
    εργ
    0.06
    кти
    0.06
    Activations Density 0.055%

    No Known Activations