© 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. 19-RESID-POST-AA
    11. 123633
    Prev
    Next
    INDEX
    Explanations

    media

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     갤로그로
    -0.06
     моб
    -0.06
     lesion
    -0.06
     Electron
    -0.06
     EditorGUILayout
    -0.06
     RC
    -0.06
     являются
    -0.06
    _music
    -0.06
    선을
    -0.06
     Gö
    -0.06
    POSITIVE LOGITS
    /oauth
    0.07
    (COLOR
    0.07
    我們
    0.07
    Const
    0.07
    (ConfigurationManager
    0.06
     loin
    0.06
    ographed
    0.06
    ()[
    0.06
     bán
    0.06
     hete
    0.06
    Activations Density 0.000%

    No Known Activations