© 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. 30166
    Prev
    Next
    INDEX
    Explanations

    columns

    np_max-act · gemini-2.0-flash

    This neuron detects schema‐definition contexts, i.e. passages describing tables and their columns.

    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
    /problem
    -0.07
    งศ
    -0.07
    antas
    -0.07
     vg
    -0.07
     Ling
    -0.07
    NER
    -0.06
    	p
    -0.06
    ner
    -0.06
     (�
    -0.06
    kg
    -0.06
    POSITIVE LOGITS
     질문
    0.07
     SR
    0.07
    τησε
    0.07
     CSA
    0.07
     DE
    0.06
     wła
    0.06
    Kick
    0.06
     inev
    0.06
     Avust
    0.06
     NYC
    0.06
    Activations Density 0.017%

    No Known Activations