© 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. 6141
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on content words in ecclesiastical or hagiographic biography passages, flagging tokens in the “life of a saint or church figure” narrative.

    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
    862
    -0.07
     ridicule
    -0.06
    Zend
    -0.06
     joker
    -0.06
    (unit
    -0.06
     goats
    -0.06
    irsch
    -0.06
     unbelie
    -0.06
     golf
    -0.06
    ()-
    -0.06
    POSITIVE LOGITS
     configuring
    0.06
    balance
    0.06
     všichni
    0.06
     evenly
    0.06
     limitation
    0.06
     adjusts
    0.06
     sono
    0.06
    ordering
    0.06
    isRequired
    0.06
     functioning
    0.06
    Activations Density 0.051%

    No Known Activations