© 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. 11-RESID-POST-AA
    11. 59323
    Prev
    Next
    INDEX
    Explanations

    colon/quote

    np_max-act · gemini-2.0-flash

    The neuron fires on JSON schema field names (i.e. keys like "address_line", "city", "state", "zip/postal code", "country").

    oai_token-act-pair · o4-mini
    Triggered by @xinyanhu8
    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
    Negative Logits
     meal
    -0.07
     cải
    -0.07
     accused
    -0.07
    関係
    -0.06
    Constants
    -0.06
    ää
    -0.06
     obligated
    -0.06
     htonl
    -0.06
     shield
    -0.06
     Dos
    -0.06
    POSITIVE LOGITS
    》（
    0.07
    ‌ی
    0.07
     Palin
    0.07
     metabol
    0.06
     उन
    0.06
    _URI
    0.06
     _('
    0.06
     dreamed
    0.06
     Hindus
    0.06
    uvre
    0.06
    Activations Density 0.016%

    No Known Activations