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. 81232
    Prev
    Next
    INDEX
    Explanations

    Important issues

    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
    HeadersHeight
    -0.07
    Ін
    -0.07
     παν
    -0.06
    kus
    -0.06
     Пар
    -0.06
    luet
    -0.06
    캐
    -0.06
     circumcision
    -0.06
    \Repositories
    -0.06
     Kensington
    -0.06
    POSITIVE LOGITS
    اصر
    0.08
     구성
    0.07
    érieur
    0.06
    èo
    0.06
    (Board
    0.06
    ضوع
    0.06
    _polygon
    0.06
    .getBody
    0.06
     Politico
    0.06
     Safe
    0.06
    Activations Density 0.188%

    No Known Activations