© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 113905
    Prev
    Next
    INDEX
    Explanations

    Japan

    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_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
    (delay
    -0.07
    莫
    -0.07
     CircularProgressIndicator
    -0.06
    dismiss
    -0.06
     �
    -0.06
    �
    -0.06
     Async
    -0.06
     IU
    -0.06
    965
    -0.06
     pigs
    -0.06
    POSITIVE LOGITS
     Nhật
    0.08
    кав
    0.07
    丸
    0.07
    uki
    0.07
     Sakura
    0.07
     Japan
    0.07
     Japanese
    0.07
    .jp
    0.07
     ECM
    0.07
     SPD
    0.07
    Activations Density 0.189%

    No Known Activations