© 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. 43474
    Prev
    Next
    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting legal citations, specifically references to numbered sections, subsections, and clause identifiers in statutory or regulatory texts.

    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
    ireccion
    -0.06
     Tex
    -0.06
     Erotik
    -0.06
    .rar
    -0.06
    .rows
    -0.06
     unchecked
    -0.06
    .img
    -0.06
     perfect
    -0.06
     PRODUCT
    -0.06
    channel
    -0.06
    POSITIVE LOGITS
     différent
    0.07
     specialize
    0.06
     INTERNATIONAL
    0.06
     Elevated
    0.06
     вт
    0.06
     cong
    0.06
     plusieurs
    0.06
     совет
    0.06
     Kurulu
    0.06
     vẫn
    0.06
    Activations Density 0.009%

    No Known Activations