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. 15-RESID-POST-AA
    6. 54070
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    nějších
    -0.07
     Peng
    -0.06
     intervening
    -0.06
     普通
    -0.06
     Вели
    -0.06
    ]):
    ↵
    -0.06
     професій
    -0.06
    .AspNet
    -0.06
     ortak
    -0.06
     Chatt
    -0.06
    POSITIVE LOGITS
     bakeka
    0.07
     necessário
    0.06
     의미
    0.06
    .pos
    0.06
    ÜM
    0.06
     bei
    0.06
                                                                                                                                    
    0.06
     psychosis
    0.06
    调整
    0.06
     важно
    0.06
    Activations Density 0.001%

    No Known Activations