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

    Neuronpedia

    Jacobian LensNEW
    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. 56832
    Prev
    Next
    INDEX
    Explanations

    page

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases that denote beauty pageants and pageant titles (e.g., “Miss,” “beauty,” “pageant,” “crowned,” “queen,” “titleholder,” “competition”).

    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
     glaciers
    -0.08
     displayed
    -0.07
    =l
    -0.07
    (messages
    -0.07
    кт
    -0.06
    樹
    -0.06
    (dead
    -0.06
    (M
    -0.06
    (Camera
    -0.06
     Mom
    -0.06
    POSITIVE LOGITS
    Soap
    0.08
    Mah
    0.08
     böl
    0.07
    emale
    0.07
    Exist
    0.06
    tring
    0.06
     sar
    0.06
    taboola
    0.06
     Establishment
    0.06
    season
    0.06
    Activations Density 0.002%

    No Known Activations