© 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. 59339
    Prev
    Next
    INDEX
    Explanations

    concludes

    np_max-act · gemini-2.0-flash

    This neuron activates on the standard concluding sentence in court opinions (e.g. “The panel unanimously concludes this case is suitable for decision without oral argument”).

    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
    _COMPLETED
    -0.07
    Messaging
    -0.07
    implicit
    -0.07
     noticing
    -0.06
    iatric
    -0.06
     Nem
    -0.06
    Compar
    -0.06
    RITE
    -0.06
    anian
    -0.06
     SAC
    -0.06
    POSITIVE LOGITS
     místa
    0.07
     drops
    0.06
    ?action
    0.06
     янва
    0.06
     už
    0.06
     outweigh
    0.06
    \r
    0.06
     moda
    0.06
    ---------↵↵
    0.06
    oggler
    0.06
    Activations Density 0.001%

    No Known Activations