© 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. 90908
    Prev
    Next
    INDEX
    Explanations

    intricate

    np_max-act · gemini-2.0-flash

    This neuron detects descriptive adjectives emphasizing elaborate, finely detailed visual elements (e.g. “intricate,” “delicate”).

    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
     fails
    -0.08
    	L
    -0.07
    媒体
    -0.07
     failing
    -0.06
     каж
    -0.06
    '>"+
    -0.06
    ","+
    -0.06
     fail
    -0.06
    Yes
    -0.06
     Sail
    -0.06
    POSITIVE LOGITS
     intricate
    0.14
     delicate
    0.09
    Construct
    0.08
     intric
    0.08
     intrig
    0.07
    碎
    0.07
    lac
    0.07
    이트
    0.07
    วง
    0.07
     Dig
    0.07
    Activations Density 0.005%

    No Known Activations