© 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. 27-RESID-POST-AA
    11. 23361
    Prev
    Next
    INDEX
    Explanations

    sudden changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _third
    -0.07
    �
    -0.07
    кул
    -0.07
     ==>
    -0.07
     sélection
    -0.07
    تور
    -0.07
    <head
    -0.06
     tư
    -0.06
    ،↵
    -0.06
     Charleston
    -0.06
    POSITIVE LOGITS
    过程
    0.08
     Avrupa
    0.06
     lantern
    0.06
    .BackgroundImage
    0.06
     drei
    0.06
     роки
    0.05
    ecký
    0.05
    .В
    0.05
    .rmi
    0.05
    ンティ
    0.05
    Activations Density 0.338%

    No Known Activations