© 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. 9440
    Prev
    Next
    INDEX
    Explanations

    print

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the occurrence of the word “printed,” as in “printed circuit boards.”

    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
    268
    -0.09
     accusations
    -0.08
    Factors
    -0.08
     حوزه
    -0.07
     Basis
    -0.07
    oxide
    -0.07
     Catalyst
    -0.07
     accused
    -0.07
     axis
    -0.07
     Rebels
    -0.07
    POSITIVE LOGITS
     print
    0.12
     Print
    0.10
     printing
    0.10
    print
    0.10
    (Print
    0.10
    Print
    0.10
    ��
    0.09
    Printer
    0.09
     imprint
    0.09
    印
    0.09
    Activations Density 0.032%

    No Known Activations