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. 90189
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    The neuron detects direct second‐person address (tokens like “you,” “your,” “you’re,” etc.) indicating sentences speaking to the reader.

    oai_token-act-pair · o4-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
    鼠
    -0.07
    Tai
    -0.07
    Black
    -0.06
    cookies
    -0.06
    '#
    -0.06
    -toggle
    -0.06
     scooter
    -0.06
    	video
    -0.06
    dress
    -0.06
    -danger
    -0.06
    POSITIVE LOGITS
     connectionString
    0.06
     continuation
    0.06
    (Roles
    0.06
     nền
    0.06
    itě
    0.06
     일을
    0.06
     �
    0.06
     lakes
    0.06
     än
    0.06
     stron
    0.06
    Activations Density 0.065%

    No Known Activations