© 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. 23-RESID-POST-AA
    11. 69058
    Prev
    Next
    INDEX
    Explanations

    geography, places, or regions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    	actor
    -0.07
    .Detail
    -0.07
     demande
    -0.06
     quý
    -0.06
    lena
    -0.06
    bundle
    -0.06
     Suche
    -0.06
     snippet
    -0.06
     Template
    -0.06
     api
    -0.06
    POSITIVE LOGITS
    ोफ
    0.07
     eff
    0.07
     ό
    0.07
     lithium
    0.07
     racist
    0.07
     dynam
    0.06
    (INPUT
    0.06
     UnsupportedOperationException
    0.06
    انت
    0.06
     citizen
    0.06
    Activations Density 0.020%

    No Known Activations