© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 20144
    Prev
    Next
    INDEX
    Explanations

    Button/keyboard configurations

    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
     challenging
    -0.08
    obre
    -0.07
     خشک
    -0.07
    比
    -0.07
    кі
    -0.07
     Walt
    -0.07
    Containers
    -0.06
    intelligence
    -0.06
    Gi
    -0.06
     bondage
    -0.06
    POSITIVE LOGITS
    inished
    0.07
    ी-
    0.06
     응
    0.06
     Swagger
    0.06
     adorned
    0.06
     rowNum
    0.06
    ойно
    0.06
     enforcing
    0.06
     fict
    0.06
     JpaRepository
    0.06
    Activations Density 0.012%

    No Known Activations