© 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. 7-RESID-POST-AA
    11. 21498
    Prev
    Next
    INDEX
    Explanations

    可以

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     тех
    -0.07
     oğlu
    -0.06
     indices
    -0.06
    SetText
    -0.06
     Montgomery
    -0.06
     koş
    -0.06
    "We
    -0.06
     catalogs
    -0.06
    lio
    -0.06
     Pump
    -0.06
    POSITIVE LOGITS
    可以
    0.16
    能够
    0.10
    ，可以
    0.10
    会
    0.09
    可
    0.09
     会
    0.08
    要
    0.08
    需要
    0.08
    能
    0.07
     bisa
    0.07
    Activations Density 0.017%

    No Known Activations