Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109966
    Prev
    Next
    INDEX
    Explanations

    History and royalty

    np_max-act · gemini-2.0-flash

    historical figures and their familial relationships, particularly within noble lineages.

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

    The neuron specifically activates on occurrences of the substring “habsburg” (i.e. references to the Habsburg dynasty).

    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
     میلی
    -0.08
    _loan
    -0.07
    WSC
    -0.07
    _intersect
    -0.07
    generate
    -0.06
     comprising
    -0.06
     perception
    -0.06
     AM
    -0.06
     tong
    -0.06
     sequential
    -0.06
    POSITIVE LOGITS
     Rodgers
    0.06
    ितन
    0.06
    繁
    0.06
    ideo
    0.06
     savings
    0.06
     Farmers
    0.06
     junto
    0.06
    sofar
    0.06
    _field
    0.06
     "','"
    0.06
    Activations Density 0.010%

    No Known Activations