© 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. 91717
    Prev
    Next
    INDEX
    Explanations

    GameObject

    np_max-act · gemini-2.0-flash

    The neuron fires on instructions about attaching or referencing Unity GameObjects or components (e.g. “attach it to a GameObject in your scene”).

    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
     corridors
    -0.08
    	left
    -0.07
     troubling
    -0.06
    _derivative
    -0.06
     analysed
    -0.06
    독
    -0.06
     Battery
    -0.06
    _delivery
    -0.06
     independ
    -0.06
     test
    -0.06
    POSITIVE LOGITS
    <GameObject
    0.09
     GameObject
    0.08
    TagName
    0.07
    friendly
    0.07
     itemView
    0.07
     (;;)
    0.07
     قالب
    0.07
     Pont
    0.07
     misconduct
    0.07
    "'
    0.06
    Activations Density 0.004%

    No Known Activations