© 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. 15-RESID-POST-AA
    11. 34310
    Prev
    Next
    INDEX
    Explanations

    schools, cities, places

    np_max-act · gemini-2.0-flash

    This neuron detects short names, nicknames, or informal/alternate forms of entity names (often shown in quotes, parentheses, or as abbreviated labels).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Home
    -0.07
     HOME
    -0.07
    .But
    -0.07
    ansas
    -0.07
    Blo
    -0.06
     corros
    -0.06
     maintenant
    -0.06
    .Real
    -0.06
    Equipment
    -0.06
    -web
    -0.06
    POSITIVE LOGITS
     περισσότε
    0.07
     изуч
    0.06
    typeparam
    0.06
     CONDITION
    0.06
    ':[
    0.06
    /]
    0.06
    %@",
    0.06
    слов
    0.06
    .symmetric
    0.06
    암
    0.06
    Activations Density 0.066%

    No Known Activations