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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 110108
    Prev
    Next
    INDEX
    Explanations

    Component

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the method‐signature tokens of Swing painting routines (e.g. “paintComponent(Graphics g)”).

    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
     credential
    -0.07
    Planning
    -0.06
     cic
    -0.06
     dục
    -0.06
     plt
    -0.06
     fellowship
    -0.06
     Hardcover
    -0.06
     fasta
    -0.06
     Timeout
    -0.06
    agation
    -0.06
    POSITIVE LOGITS
     Crosby
    0.07
    HasBeen
    0.07
    aciones
    0.07
    .ResponseWriter
    0.07
                		
    0.07
    485
    0.07
       
    0.06
     UCLA
    0.06
    ='-
    0.06
    chen
    0.06
    Activations Density 0.001%

    No Known Activations