Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53792
    Prev
    Next
    INDEX
    Explanations

    periods

    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
     "%.
    -0.06
    OUNTER
    -0.06
    ظهر
    -0.06
    υ
    -0.06
     grades
    -0.06
     """
    -0.06
    izarre
    -0.05
     Winner
    -0.05
     REMOVE
    -0.05
    ]**
    -0.05
    POSITIVE LOGITS
    .metric
    0.07
     Tổng
    0.07
    ]-$
    0.07
    :len
    0.07
     �
    0.07
     ihren
    0.07
    OO
    0.06
    .Admin
    0.06
     Ahead
    0.06
     přen
    0.06
    Activations Density 0.001%

    No Known Activations