© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129788
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron activates on legal document citations and enumerated statutory or case‐law reference numbers (e.g. section symbols, numeric subsections, and case cite numbers).

    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
     потреб
    -0.06
     buckle
    -0.06
    .old
    -0.06
    endants
    -0.06
    (bool
    -0.06
     Blend
    -0.06
    Completion
    -0.06
     conceded
    -0.06
    푸
    -0.06
    ADDING
    -0.06
    POSITIVE LOGITS
    idla
    0.06
    _chart
    0.06
     BufferedImage
    0.06
     singers
    0.06
     predators
    0.06
    .ColumnStyle
    0.06
     svob
    0.06
    ọng
    0.06
    μα
    0.06
    реть
    0.06
    Activations Density 0.014%

    No Known Activations