© 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. 37964
    Prev
    Next
    INDEX
    Explanations

    compliance

    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
     cosa
    -0.07
    ausal
    -0.06
     inner
    -0.06
    ="{{
    -0.06
    自
    -0.06
     MESSAGE
    -0.06
    izacion
    -0.06
    ์โ
    -0.06
     unittest
    -0.06
     jeopard
    -0.06
    POSITIVE LOGITS
    ектив
    0.07
     heir
    0.06
    proxy
    0.06
    Images
    0.06
     fighters
    0.06
    ції
    0.06
    νας
    0.06
     spontaneous
    0.06
    STRUCTION
    0.06
     Ens
    0.06
    Activations Density 0.000%

    No Known Activations