© 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. 47819
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment/harm

    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
    �权
    -0.07
    .assertEqual
    -0.06
    .exp
    -0.06
    스토
    -0.06
     اف
    -0.06
    ーン
    -0.06
     Cel
    -0.06
    .cast
    -0.06
    昇
    -0.06
    uckets
    -0.06
    POSITIVE LOGITS
     avere
    0.08
     altercation
    0.07
     Alvarez
    0.07
     sonu
    0.06
    155
    0.06
     тобі
    0.06
     expose
    0.06
     agregar
    0.06
     groundbreaking
    0.06
    利
    0.06
    Activations Density 0.004%

    No Known Activations