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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74901
    Prev
    Next
    INDEX
    Explanations

    what

    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
     dragons
    -0.06
     hurt
    -0.06
    狗
    -0.06
    dff
    -0.06
    ンデ
    -0.06
    hp
    -0.06
    0
    -0.06
    icio
    -0.05
    90
    -0.05
    oreach
    -0.05
    POSITIVE LOGITS
    тор
    0.07
    Concrete
    0.07
     UNIVERSITY
    0.07
     defy
    0.07
     elevate
    0.07
    iế
    0.06
    China
    0.06
     червня
    0.06
    /book
    0.06
    ระด
    0.06
    Activations Density 0.096%

    No Known Activations