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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56087
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric expressions (digits, decades, percentages, and decimal numbers) in the 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
     humidity
    -0.08
    richTextPanel
    -0.07
    .validator
    -0.07
    (rect
    -0.06
     Wash
    -0.06
     Cylinder
    -0.06
     Weekend
    -0.06
    _Post
    -0.06
    前往
    -0.06
    аст
    -0.06
    POSITIVE LOGITS
     función
    0.07
    NSData
    0.07
     случ
    0.06
     hatır
    0.06
    |--
    0.06
    スマ
    0.06
    [String
    0.06
     �
    0.06
    	function
    0.06
    edido
    0.06
    Activations Density 0.109%

    No Known Activations