© 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. 79615
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
     assisting
    -0.06
     referral
    -0.06
     sore
    -0.06
    leigh
    -0.06
    TYPE
    -0.06
    inar
    -0.06
     indicate
    -0.06
     Ham
    -0.06
     Diesel
    -0.06
     спор
    -0.06
    POSITIVE LOGITS
    mpz
    0.07
    modification
    0.07
    (separator
    0.06
     sesso
    0.06
     kadın
    0.06
    щі
    0.06
     عنه
    0.06
    něn
    0.06
    ลงท
    0.06
     çı
    0.06
    Activations Density 0.029%

    No Known Activations