© 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. 11-RESID-POST-AA
    11. 46861
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    बल
    -0.07
    endo
    -0.07
     پر
    -0.07
     americ
    -0.06
     کر
    -0.06
     آس
    -0.06
     yı
    -0.06
     Whereas
    -0.06
     GFX
    -0.06
     사라
    -0.06
    POSITIVE LOGITS
    flare
    0.06
     archivos
    0.06
     Pornhub
    0.06
    ییر
    0.06
    Crop
    0.06
    يمكن
    0.06
    iological
    0.06
     -->
↵
↵
    0.06
     شود
    0.06
    _AHB
    0.06
    Activations Density 0.096%

    No Known Activations