© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 124617
    Prev
    Next
    INDEX
    Explanations

    Criticisms of Trump

    np_max-act · gemini-2.0-flash

    profiles of American politicians, particularly focusing on their backgrounds, political positions, and notable actions during their presidencies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     shepherd
    -0.07
    817
    -0.07
     Spokane
    -0.07
    ombine
    -0.06
    stories
    -0.06
     brands
    -0.06
    ;:;:
    -0.06
    morph
    -0.06
    갑
    -0.06
     oluşan
    -0.06
    POSITIVE LOGITS
    ;",↵
    0.07
    (TEXT
    0.06
    gresql
    0.06
    [String
    0.06
    route
    0.06
     ☆
    0.06
    .IntegerField
    0.06
    _PROVIDER
    0.06
     ttk
    0.06
    \htdocs
    0.06
    Activations Density 0.046%

    No Known Activations