© 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. 128874
    Prev
    Next
    INDEX
    Explanations

    Veins

    np_max-act · gemini-2.0-flash

    This neuron responds to the substring “ular” (as in the “ular” ending of anatomical terms like “jugular”).

    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
    隨
    -0.07
     Reply
    -0.07
    Day
    -0.06
    ün
    -0.06
    explained
    -0.06
     Mun
    -0.06
     Zwe
    -0.06
     Sat
    -0.06
     acidic
    -0.06
     invariant
    -0.06
    POSITIVE LOGITS
     Cumhurbaşkanı
    0.07
    liğ
    0.07
    都
    0.06
    	record
    0.06
     jquery
    0.06
    orderBy
    0.06
    isEqual
    0.06
     adına
    0.06
    BOOLE
    0.06
     serializers
    0.06
    Activations Density 0.003%

    No Known Activations