© 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. 110143
    Prev
    Next
    INDEX
    Explanations

    Refresh

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “refresh” (and its variants) in code identifiers and strings, i.e. tokens related to pull-to-refresh or refresh control names.

    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
     aficion
    -0.07
    ocy
    -0.07
    čný
    -0.07
     whispers
    -0.06
    )item
    -0.06
    ستم
    -0.06
     dělat
    -0.06
    _reg
    -0.06
    _GAME
    -0.06
     Paras
    -0.06
    POSITIVE LOGITS
     распростран
    0.07
    ,↵
    0.07
    _Y
    0.07
     graffiti
    0.06
     GC
    0.06
    country
    0.06
    年の
    0.06
     citizen
    0.06
     ‫
    0.06
    -meter
    0.06
    Activations Density 0.002%

    No Known Activations