© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109401
    Prev
    Next
    INDEX
    Explanations

    legislators

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of political offices and legislative service (e.g. “member of the Virginia House of Delegates,” “served as Senator,” “state legislator,” etc.).

    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
    Pocket
    -0.07
     پرو
    -0.07
    .Properties
    -0.06
    xygen
    -0.06
    elas
    -0.06
     ortadan
    -0.06
    \Data
    -0.06
     accessories
    -0.06
     setPassword
    -0.06
     borderBottom
    -0.06
    POSITIVE LOGITS
    [${
    0.07
     story
    0.07
    (cfg
    0.06
    ória
    0.06
     ваг
    0.06
     hyper
    0.06
     ł
    0.06
    \ActiveForm
    0.06
     Spoj
    0.06
     approximation
    0.06
    Activations Density 0.027%

    No Known Activations