© 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. 48025
    Prev
    Next
    INDEX
    Explanations

    1 or 2

    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_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
     toes
    -0.07
     बड
    -0.06
     代
    -0.06
     Dio
    -0.06
     Farr
    -0.06
    _AGENT
    -0.06
    ์ท
    -0.06
     �
    -0.06
     elő
    -0.06
     shiny
    -0.06
    POSITIVE LOGITS
     ferment
    0.07
     mystical
    0.07
    ,,,
    0.06
     knockout
    0.06
    मत
    0.06
     rects
    0.06
     rc
    0.06
    Closing
    0.06
     în
    0.06
     mois
    0.06
    Activations Density 0.068%

    No Known Activations