© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41456
    Prev
    Next
    INDEX
    Explanations

    switch

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the verb “switch,” especially in phrases like “switch between” or “switch [X] in a click.”

    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
    RenderTarget
    -0.07
    Msp
    -0.07
    yaw
    -0.06
     '
↵
    -0.06
     Deborah
    -0.06
     CJ
    -0.06
    _content
    -0.06
    _NO
    -0.06
    .acc
    -0.06
    -desc
    -0.06
    POSITIVE LOGITS
     switched
    0.09
     switch
    0.08
     switching
    0.08
    .locale
    0.07
    	switch
    0.07
     muz
    0.07
    澳
    0.07
     waters
    0.07
    關
    0.07
     useMemo
    0.06
    Activations Density 0.020%

    No Known Activations