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. 81109
    Prev
    Next
    INDEX
    Explanations

    ="

    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
    бі
    -0.06
    bas
    -0.06
    Feedback
    -0.06
     uyg
    -0.06
    АН
    -0.06
    emand
    -0.06
    hů
    -0.06
    telefono
    -0.06
    าค
    -0.06
    休
    -0.06
    POSITIVE LOGITS
     происходит
    0.07
     можно
    0.07
    ?”
    0.07
    orr
    0.06
     cylinder
    0.06
    сяг
    0.06
     四
    0.06
    自動
    0.06
    ugh
    0.06
     collagen
    0.06
    Activations Density 0.001%

    No Known Activations