© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 77578
    Prev
    Next
    INDEX
    Explanations

    debt

    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
    네
    -0.06
     cruc
    -0.06
    dp
    -0.06
    numer
    -0.06
    313
    -0.06
     Rape
    -0.06
     plainly
    -0.06
     looks
    -0.06
     presentations
    -0.06
     PU
    -0.06
    POSITIVE LOGITS
    井
    0.08
     embell
    0.07
     ジ
    0.07
     کسب
    0.06
    .EntityFrameworkCore
    0.06
     hợp
    0.06
    �
    0.06
     �
    0.06
    裏
    0.06
    лика
    0.06
    Activations Density 0.013%

    No Known Activations