© 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. 27-RESID-POST-AA
    11. 13100
    Prev
    Next
    INDEX
    Explanations

    to

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     gases
    -0.07
    (cv
    -0.06
    ,
    -0.06
    -0.06
     voc
    -0.06
    _subset
    -0.06
     puzzle
    -0.06
     verse
    -0.06
    .,
    -0.06
    ().↵
    -0.06
    POSITIVE LOGITS
     폐
    0.08
     dismal
    0.07
    λι
    0.06
     fearless
    0.06
    шается
    0.06
     неприят
    0.06
     มหาว
    0.06
     endIndex
    0.06
     Naruto
    0.06
     기본
    0.06
    Activations Density 0.029%

    No Known Activations