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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38819
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on the formal structure of U.S. court‐opinion documents – things like case captions and section headings (roman-numeral labels, “BACKGROUND,” “OPINION,” “PER CURIAM,” etc.).

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

    legal terminology and references pertaining to court cases and appeals.

    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
     Drink
    -0.07
    Theo
    -0.07
    zia
    -0.06
     Oro
    -0.06
    Rows
    -0.06
    ورا
    -0.06
     tooth
    -0.06
     Raj
    -0.06
     spouse
    -0.06
     press
    -0.06
    POSITIVE LOGITS
    ，全
    0.06
    AREN
    0.06
    έντ
    0.06
    ائد
    0.06
     incompetent
    0.06
     eagerly
    0.06
    开展
    0.06
    @GetMapping
    0.06
     امتی
    0.06
     durumda
    0.06
    Activations Density 0.005%

    No Known Activations