© 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. 56117
    Prev
    Next
    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash

    SQL commands and queries used to manipulate or retrieve data from database tables.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires whenever the text refers to or names SQL tables—i.e. it detects the keyword “table” (and related table identifiers) in SQL queries.

    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
     Fighters
    -0.08
    .getString
    -0.07
    prevState
    -0.07
    Americans
    -0.07
     शत
    -0.07
     Legends
    -0.06
    -up
    -0.06
     evangel
    -0.06
     farmers
    -0.06
    ुपय
    -0.06
    POSITIVE LOGITS
     bulky
    0.06
     avere
    0.06
    ookie
    0.06
     الى
    0.06
    ,line
    0.06
    )value
    0.06
    (jj
    0.06
    647
    0.06
    :UI
    0.06
    $key
    0.06
    Activations Density 0.016%

    No Known Activations