© 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
    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. 129863
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron detects in‐text citation markers, i.e. reference numbers (and their surrounding brackets/parentheses) in academic or technical documents.

    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
    ेट
    -0.07
     BACKGROUND
    -0.07
    avern
    -0.07
     Regression
    -0.06
    .Location
    -0.06
    benchmark
    -0.06
    电视
    -0.06
    tower
    -0.06
     Sheep
    -0.06
    ギ
    -0.06
    POSITIVE LOGITS
     instit
    0.07
    (".",
    0.06
     {\↵
    0.06
     ".";↵
    0.06
    дн
    0.06
     Wildcats
    0.06
    yps
    0.06
     جر
    0.06
     dors
    0.06
     ana
    0.06
    Activations Density 0.003%

    No Known Activations