© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 28524
    Prev
    Next
    INDEX
    Explanations

    The Voice

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.07
     enn
    -0.07
     ánh
    -0.07
     ruins
    -0.07
    ریب
    -0.06
    意义
    -0.06
     собы
    -0.06
    .bounds
    -0.06
     interruption
    -0.06
    irling
    -0.06
    POSITIVE LOGITS
    ecx
    0.06
    parts
    0.06
    disciplinary
    0.06
    156
    0.06
    :UIButtonType
    0.06
    ++++++++
    0.06
    uels
    0.06
    iid
    0.06
     sä
    0.05
     αδ
    0.05
    Activations Density 0.002%

    No Known Activations