© 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. 76932
    Prev
    Next
    INDEX
    Explanations

    ous

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to mentions of mucus/mucin—especially “mucous” or “mucin‐type glycoprotein” terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    words related to mucosal components and their role in various biological processes.

    oai_token-act-pair · gpt-4o-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
    监听页面
    -0.07
    otomy
    -0.07
    _continue
    -0.06
    東京
    -0.06
    γι
    -0.06
     araştırma
    -0.06
     ハ
    -0.06
     Fisher
    -0.06
     Этот
    -0.06
    شركة
    -0.06
    POSITIVE LOGITS
     对
    0.07
     streaming
    0.07
     先
    0.07
     crater
    0.06
     equipo
    0.06
    ;margin
    0.06
     (((
    0.06
    тоф
    0.06
     PRICE
    0.06
    	ss
    0.06
    Activations Density 0.003%

    No Known Activations