© 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. 7-RESID-POST-AA
    11. 36596
    Prev
    Next
    INDEX
    Explanations

    defensive

    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
    Negative Logits
     revolving
    -0.07
     token
    -0.07
     Glas
    -0.07
     Prepare
    -0.06
     istedi
    -0.06
    ाण
    -0.06
     announced
    -0.06
     taxi
    -0.06
     inhibitors
    -0.06
     Nob
    -0.06
    POSITIVE LOGITS
    shutdown
    0.06
    .dateTimePicker
    0.06
     ContentValues
    0.06
    Responder
    0.06
    hopefully
    0.06
    categorias
    0.06
    orage
    0.06
     hindi
    0.06
    ~~
    0.06
    стве
    0.06
    Activations Density 0.004%

    No Known Activations