© 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. 68945
    Prev
    Next
    INDEX
    Explanations

    physics

    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
    -approved
    -0.07
    Production
    -0.07
     Running
    -0.07
    /memory
    -0.07
    -rights
    -0.07
     months
    -0.07
     FAILED
    -0.07
     Manufacturing
    -0.07
    Council
    -0.07
     Liberty
    -0.07
    POSITIVE LOGITS
     прояв
    0.07
     alacak
    0.06
     MessageBoxButtons
    0.06
    хов
    0.06
    บ
    0.06
     ऐस
    0.06
     прок
    0.06
     HAPP
    0.06
     prostě
    0.05
     raspberry
    0.05
    Activations Density 0.060%

    No Known Activations