© 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. 22679
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     weekly
    -0.07
     beverage
    -0.06
    /people
    -0.06
     medial
    -0.06
     Fant
    -0.06
     Accident
    -0.06
     застосування
    -0.06
     ";
    -0.06
     DIM
    -0.06
    publish
    -0.06
    POSITIVE LOGITS
     zeigt
    0.06
    +-+-
    0.06
     ejaculation
    0.06
     ден
    0.06
    ック
    0.06
    lij
    0.06
     Ό
    0.06
     Пост
    0.06
     sake
    0.06
    なる
    0.06
    Activations Density 0.006%

    No Known Activations