© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68808
    Prev
    Next
    INDEX
    Explanations

    reload

    np_max-act · gemini-2.0-flash

    The neuron activates on terms and code patterns that concern reloading or refreshing content (pages, views, grids, data).

    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
    block
    -0.07
     Yankee
    -0.07
     Gavin
    -0.06
     Jazz
    -0.06
    つけ
    -0.06
    ॉल
    -0.06
     thinks
    -0.06
     frustration
    -0.06
     Ruth
    -0.06
     stripe
    -0.06
    POSITIVE LOGITS
     двиг
    0.06
    -animate
    0.06
     خانواده
    0.06
     FetchType
    0.06
     إليه
    0.06
    ----------------------------------------------------------------
    0.06
     діяль
    0.06
    	reload
    0.06
    EDIT
    0.06
    NewItem
    0.06
    Activations Density 0.012%

    No Known Activations