© 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
    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. 29967
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    The neuron fires on statutory‐style citations and section references (e.g. “42 U.S.C. §…,” numeric circuit citations, decimal page or paragraph numbers), i.e. legal code and statute citations.

    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
    .Surface
    -0.07
    .writeInt
    -0.06
    Products
    -0.06
     večer
    -0.06
     Gamer
    -0.06
    (ff
    -0.06
    ätt
    -0.06
    ================================
    -0.06
     смесь
    -0.06
    Acceleration
    -0.06
    POSITIVE LOGITS
    ้าของ
    0.07
    _mot
    0.07
    590
    0.07
    (images
    0.07
    .IsAny
    0.06
    -lines
    0.06
    osis
    0.06
     descriptor
    0.06
    Minimum
    0.06
    close
    0.06
    Activations Density 0.013%

    No Known Activations