© 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. 7-RESID-POST-AA
    11. 64965
    Prev
    Next
    INDEX
    Explanations

    (

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     stainless
    -0.07
     decipher
    -0.07
     findAll
    -0.07
     sürdür
    -0.07
    718
    -0.06
     ridiculous
    -0.06
    ford
    -0.06
     �
    -0.06
     μετα
    -0.06
     جمله
    -0.06
    POSITIVE LOGITS
    мир
    0.06
    ationale
    0.06
    landing
    0.06
    eam
    0.06
    ||
    0.06
     militias
    0.06
     approval
    0.06
    레벨
    0.06
    鹿
    0.06
     liar
    0.06
    Activations Density 0.003%

    No Known Activations