© 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. 44488
    Prev
    Next
    INDEX
    Explanations

    8

    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
    Not in Any Lists

    No Comments

    Negative Logits
    たく
    -0.07
     GOOD
    -0.06
     ей
    -0.06
    ินการ
    -0.06
    冒
    -0.06
    牧
    -0.06
     illustrates
    -0.06
    -0.06
    ibraries
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     витами
    0.07
     getState
    0.06
    .cb
    0.06
    jsonData
    0.06
     usu
    0.06
    .Volume
    0.06
     viewBox
    0.06
    toInt
    0.06
    optional
    0.06
    loggedin
    0.06
    Activations Density 0.001%

    No Known Activations