© 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. 115008
    Prev
    Next
    INDEX
    Explanations

    armenian genocide

    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
    Iterations
    -0.06
     insights
    -0.06
     ю
    -0.06
     advocate
    -0.06
    ATABASE
    -0.06
     Fo
    -0.06
     useClass
    -0.06
    ы
    -0.06
    ╝
    -0.06
     Со
    -0.06
    POSITIVE LOGITS
     jov
    0.06
     hesitation
    0.06
    oine
    0.06
     Cassandra
    0.06
     вер
    0.06
     refere
    0.06
    ombok
    0.06
    ;q
    0.06
     işte
    0.06
     deprived
    0.06
    Activations Density 0.046%

    No Known Activations