© 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. 42866
    Prev
    Next
    INDEX
    Explanations

    '80s

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric decade references (e.g. “80s,” “90s,” “1980s,” “1990s”).

    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
     consts
    -0.07
    ору
    -0.06
    leftrightarrow
    -0.06
    (ref
    -0.06
     replic
    -0.06
    міну
    -0.06
     kèo
    -0.06
     mediocre
    -0.06
    (include
    -0.06
     Reyes
    -0.06
    POSITIVE LOGITS
     kk
    0.07
          
↵
    0.07
    شار
    0.07
    lie
    0.06
    AtPath
    0.06
    身体
    0.06
    .fil
    0.06
    家庭
    0.06
    รายงาน
    0.06
    vem
    0.06
    Activations Density 0.017%

    No Known Activations