© 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
    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. 124963
    Prev
    Next
    INDEX
    Explanations

    sports events

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting numeric and statistical tokens—years, scores, counts, measurements, and similar factual figures—especially in sports‐related text.

    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
    iments
    -0.07
     cố
    -0.06
    aná
    -0.06
     dancers
    -0.06
     theme
    -0.06
     Cou
    -0.06
     film
    -0.06
    共同
    -0.06
     Mavericks
    -0.06
    Ted
    -0.06
    POSITIVE LOGITS
    шая
    0.07
    charm
    0.07
    ={({
    0.07
    (API
    0.07
     Ft
    0.06
    _DYNAMIC
    0.06
     الوص
    0.06
    。また
    0.06
    (Item
    0.06
    Meal
    0.06
    Activations Density 0.039%

    No Known Activations