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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84703
    Prev
    Next
    INDEX
    Explanations

    young age

    np_max-act · gemini-2.0-flash

    This neuron activates on words referring to sovereigns and their offices (e.g., emperor, empress, lord, heir).

    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
     Aud
    -0.07
     Sher
    -0.07
    wort
    -0.06
     Switch
    -0.06
     př
    -0.06
    cy
    -0.06
    17
    -0.06
    filtr
    -0.06
    elig
    -0.06
    atti
    -0.06
    POSITIVE LOGITS
     Advantage
    0.06
    ,idx
    0.06
    のような
    0.06
     boasts
    0.06
    Capacity
    0.06
    .jsdelivr
    0.06
     crank
    0.06
    ulario
    0.06
     τους
    0.06
    .componentInstance
    0.05
    Activations Density 0.047%

    No Known Activations