© 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. 74816
    Prev
    Next
    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the term “address” (e.g. tokens naming or referring to address fields) in database and code contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    instructions or descriptions related to database schema design, particularly involving tables and their structures.

    oai_token-act-pair · gpt-4o-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
    ListItem
    -0.07
    periments
    -0.06
     Rays
    -0.06
    relay
    -0.06
    restart
    -0.06
     tuition
    -0.06
    Ryan
    -0.06
     erotici
    -0.06
     їм
    -0.06
    buttons
    -0.06
    POSITIVE LOGITS
     ğ
    0.07
     |--
    0.07
     FAA
    0.06
    nbsp
    0.06
     searching
    0.06
    etr
    0.06
     flaming
    0.06
    .POS
    0.06
     πε
    0.06
     oppos
    0.06
    Activations Density 0.018%

    No Known Activations