© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 84371
    Prev
    Next
    INDEX
    Explanations

    technical processes and rules

    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
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.06
    「あ
    -0.06
     �
    -0.06
    İTESİ
    -0.06
     «
    -0.06
    .TypeOf
    -0.06
     سال
    -0.06
     Стар
    -0.06
    tributes
    -0.06
     ful
    -0.05
    POSITIVE LOGITS
     goggles
    0.07
    persons
    0.07
    (register
    0.07
     exit
    0.07
    思想
    0.07
    음
    0.07
    илася
    0.07
     Lake
    0.07
     infinite
    0.07
    |
↵
    0.06
    Activations Density 0.327%

    No Known Activations