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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 122541
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    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
     undes
    -0.07
     пользоват
    -0.07
     UIControl
    -0.06
    ën
    -0.06
     gris
    -0.06
    .sys
    -0.06
    .jobs
    -0.06
    <J
    -0.06
    xaf
    -0.06
    intro
    -0.06
    POSITIVE LOGITS
     đây
    0.06
     conducts
    0.06
    」,
    0.06
     kart
    0.06
     ارتف
    0.06
    =p
    0.06
    _maker
    0.06
     """↵↵
    0.06
    .protocol
    0.06
     daň
    0.05
    Activations Density 0.075%

    No Known Activations