© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15-RESID-POST-AA
    11. 28814
    Prev
    Next
    INDEX
    Explanations

    parentheses and equals

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     floating
    -0.07
    .Absolute
    -0.07
     her
    -0.07
    ’ya
    -0.06
    Her
    -0.06
     Gros
    -0.06
    ριά
    -0.06
    .ToolStripSeparator
    -0.06
     �
    -0.06
     Hera
    -0.06
    POSITIVE LOGITS
     ↓
    0.06
     ness
    0.06
    ลล
    0.06
     '';
    0.06
    seite
    0.06
    셨
    0.06
     اساس
    0.06
     παρα
    0.06
     نتایج
    0.06
     taxpayer
    0.06
    Activations Density 0.038%

    No Known Activations