© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73628
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash

    The neuron responds strongly to the contracted “’s” token (e.g. she’s, it’s) whenever it appears.

    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
    )){
    -0.07
     Since
    -0.06
     SR
    -0.06
     торгів
    -0.06
     بلغ
    -0.06
    experience
    -0.06
     glory
    -0.06
     CX
    -0.06
     имени
    -0.06
     reciprocal
    -0.06
    POSITIVE LOGITS
    .goods
    0.07
    booking
    0.06
    ,Th
    0.06
    ・・・↵↵
    0.06
    	
    ↵
    ↵
    0.06
     będzie
    0.06
     sessionFactory
    0.06
        ↵↵
    0.06
    ettle
    0.06
    iyordu
    0.06
    Activations Density 0.021%

    No Known Activations