© 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. 18714
    Prev
    Next
    INDEX
    Explanations

    category theory

    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
     　 　
    -0.07
    िम
    -0.07
     Su
    -0.07
    Lewis
    -0.07
     ．
    -0.07
     Pi
    -0.07
    タ
    -0.07
     furry
    -0.07
     Jin
    -0.07
     strncmp
    -0.07
    POSITIVE LOGITS
     TForm
    0.06
     그녀
    0.06
     Methods
    0.06
    paced
    0.06
     Orientation
    0.06
    онів
    0.06
     Freud
    0.06
     easily
    0.05
     parted
    0.05
    етель
    0.05
    Activations Density 0.017%

    No Known Activations