© 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. 44316
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash

    The neuron detects Korean verb stems that denote processes or actions (e.g. 조사, 나누, 발전, 선호, 유도).

    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
    ’ve
    -0.08
    еру
    -0.07
    've
    -0.07
    」
    -0.06
    ’s
    -0.06
    ’ll
    -0.06
    's
    -0.06
     herkes
    -0.06
    (draw
    -0.06
     eradicate
    -0.06
    POSITIVE LOGITS
    -comm
    0.08
     Domino
    0.07
     insp
    0.07
     conex
    0.07
     उपय
    0.07
    文献
    0.07
     měl
    0.06
    .addComponent
    0.06
    　↵
    0.06
    انت
    0.06
    Activations Density 0.035%

    No Known Activations