© 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. 110600
    Prev
    Next
    INDEX
    Explanations

    priest

    np_max-act · gemini-2.0-flash

    The neuron fires on words referring to priests or the priesthood (e.g., “priest,” “priestly,” “priesthood”).

    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
    AMP
    -0.06
    anvas
    -0.06
    System
    -0.06
    amp
    -0.06
     hãng
    -0.06
     gamer
    -0.06
    324
    -0.06
     Wang
    -0.06
     �
    -0.06
     pokus
    -0.06
    POSITIVE LOGITS
     Priest
    0.12
     priesthood
    0.10
     priest
    0.09
     priests
    0.09
    �
    0.07
    eid
    0.07
    riott
    0.07
    PDOException
    0.07
    vault
    0.07
     Rossi
    0.07
    Activations Density 0.003%

    No Known Activations