© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7561
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    np_max-act · gemini-2.0-flash

    The neuron fires on the Chinese meta‐labels marking the user’s query (e.g. the tokens “用户” and “问题”).

    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
     lxml
    -0.07
     curing
    -0.07
     Strateg
    -0.06
     Hàng
    -0.06
     Regents
    -0.06
     있을
    -0.06
    _Product
    -0.06
     recon
    -0.06
    肉
    -0.06
     Proposition
    -0.06
    POSITIVE LOGITS
     Pete
    0.08
     uygulama
    0.07
    ftp
    0.06
     літерату
    0.06
    	menu
    0.06
     hayvan
    0.06
    entlich
    0.06
    ABS
    0.06
    Think
    0.06
    compact
    0.06
    Activations Density 0.001%

    No Known Activations