© 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. 91659
    Prev
    Next
    INDEX
    Explanations

    meals

    np_max-act · gemini-2.0-flash

    This neuron detects meal‐type headings (e.g., “Breakfast,” “Lunch,” “Dinner,” “Snacks”) in the meal‐plan text.

    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
     incons
    -0.07
     pledge
    -0.06
     hott
    -0.06
    监督
    -0.06
     ภ
    -0.06
     ули
    -0.06
     decryption
    -0.06
     acknowledged
    -0.06
     month
    -0.06
    -legged
    -0.06
    POSITIVE LOGITS
    /window
    0.07
     BCE
    0.07
    (){}↵↵
    0.07
    ceb
    0.06
     بودند
    0.06
     طلا
    0.06
     HWND
    0.06
     sudo
    0.06
    StackTrace
    0.06
    ЕТ
    0.06
    Activations Density 0.005%

    No Known Activations