© 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. 19-RESID-POST-AA
    6. 35614
    Prev
    Next
    INDEX
    Explanations

    compliance

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (acc
    -0.07
    混合
    -0.06
    алу
    -0.06
     tabletop
    -0.06
     Machine
    -0.06
     Deep
    -0.06
     خشک
    -0.06
     thereof
    -0.06
    iyan
    -0.06
     příspě
    -0.06
    POSITIVE LOGITS
    classified
    0.07
    external
    0.07
     çat
    0.07
     subprocess
    0.06
     meals
    0.06
     شد
    0.06
     thể
    0.06
    >',↵
    0.06
    ували
    0.06
     �
    0.06
    Activations Density 0.000%

    No Known Activations