© 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. 59192
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    The neuron fires on generic discourse markers—words like “such,” “according,” “i.e.,” and similar tokens that introduce definitions, examples, or elaborations.

    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
     Russians
    -0.06
     вч
    -0.06
     crushers
    -0.06
    _phrase
    -0.06
     Crushers
    -0.06
    817
    -0.06
     Lei
    -0.06
     arma
    -0.06
    (ds
    -0.06
    test
    -0.06
    POSITIVE LOGITS
     PORT
    0.07
    Alchemy
    0.06
     Teams
    0.06
     Printable
    0.06
    Demo
    0.06
    اف
    0.06
    hapus
    0.06
     Druid
    0.06
    िलन
    0.06
    ارة
    0.06
    Activations Density 0.027%

    No Known Activations