© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 18583
    Prev
    Next
    INDEX
    Explanations

    conversations with people

    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
     sched
    -0.07
    iance
    -0.07
    orting
    -0.06
     ek
    -0.06
    _ast
    -0.06
    ند
    -0.06
     ander
    -0.06
    _strike
    -0.06
    otec
    -0.06
    ار
    -0.06
    POSITIVE LOGITS
    лей
    0.07
    <GameObject
    0.07
     readily
    0.06
     收
    0.06
     Syrians
    0.06
    xAC
    0.06
    _INSTALL
    0.06
    Nation
    0.06
    Rot
    0.06
     Elon
    0.06
    Activations Density 0.012%

    No Known Activations