Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78926
    Prev
    Next
    INDEX
    Explanations

    empowerment

    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
    buy
    -0.07
     десяти
    -0.07
     demonstrated
    -0.07
     travels
    -0.06
    TCHA
    -0.06
     sticking
    -0.06
     собою
    -0.06
    SUB
    -0.06
     beige
    -0.06
    		 ↵
    -0.06
    POSITIVE LOGITS
     empowering
    0.15
     empower
    0.14
     empowered
    0.13
     empowerment
    0.10
    ิม
    0.08
    VK
    0.07
     ERC
    0.07
    行動
    0.07
    Emp
    0.07
     encouragement
    0.07
    Activations Density 0.005%

    No Known Activations