© 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. 15-RESID-POST-AA
    11. 18734
    Prev
    Next
    INDEX
    Explanations

    Lists of facts/information

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     raises
    -0.06
    be
    -0.06
     GH
    -0.06
    _ground
    -0.06
     Jahre
    -0.06
     flats
    -0.06
     rises
    -0.06
    EMS
    -0.06
     Pare
    -0.06
    ("//
    -0.06
    POSITIVE LOGITS
     specificity
    0.07
    tensorflow
    0.06
     partic
    0.06
     Document
    0.06
     onların
    0.06
     founding
    0.06
     어려
    0.06
     lux
    0.06
    stice
    0.06
     appearance
    0.06
    Activations Density 0.008%

    No Known Activations