© 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. 59074
    Prev
    Next
    INDEX
    Explanations

    fa

    np_max-act · gemini-2.0-flash

    The neuron fires on the “fa” tokens in HTML class attributes indicating Font Awesome icon usage.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ournals
    -0.06
    .AI
    -0.06
    scanner
    -0.06
    .Graphics
    -0.06
    код
    -0.06
    ergus
    -0.06
     ListViewItem
    -0.06
     isize
    -0.05
    chk
    -0.05
    ickými
    -0.05
    POSITIVE LOGITS
    _-
    0.07
     terrifying
    0.07
     Và
    0.07
     Svg
    0.07
     fals
    0.07
     ee
    0.07
     daddy
    0.07
    =[];↵
    0.07
     homosexual
    0.06
     Sa
    0.06
    Activations Density 0.001%

    No Known Activations