© 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. 11-RESID-POST-AA
    11. 101221
    Prev
    Next
    INDEX
    Explanations

    -

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     เก
    -0.08
     TR
    -0.07
    ')↵↵
    -0.06
    ,self
    -0.06
     mingle
    -0.06
     freshly
    -0.06
    Keeping
    -0.06
    :])↵
    -0.06
    "↵↵↵↵
    -0.06
    (unique
    -0.06
    POSITIVE LOGITS
     exclusively
    0.07
    ゃ
    0.07
     anyways
    0.07
    nts
    0.06
     bob
    0.06
    .bill
    0.06
     菲
    0.06
     eleg
    0.06
    ects
    0.06
     прави
    0.06
    Activations Density 0.002%

    No Known Activations