© 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. 11-RESID-POST-AA
    11. 76276
    Prev
    Next
    INDEX
    Explanations

    return

    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
    copies
    -0.06
     Ft
    -0.06
     Julian
    -0.06
    icrobial
    -0.06
    ,,
    -0.06
     tripod
    -0.06
     stripes
    -0.06
    adena
    -0.06
     witches
    -0.06
     Providence
    -0.06
    POSITIVE LOGITS
     축구
    0.07
    manager
    0.06
    ROPERTY
    0.06
    getAttribute
    0.06
    ıyoruz
    0.06
     skyrocket
    0.06
    }.
    0.06
     İngiliz
    0.06
     yield
    0.06
    分类
    0.06
    Activations Density 0.002%

    No Known Activations