© 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. 108907
    Prev
    Next
    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash

    This neuron activates on temporal expressions—words denoting times or dates (e.g., days of the week, “week,” “month,” “year,” etc.).

    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
    �
    -0.06
    -training
    -0.06
    انگلیسی
    -0.06
    村
    -0.06
     피
    -0.06
     educ
    -0.06
    Repositories
    -0.06
     Dark
    -0.06
    (td
    -0.06
     Swedish
    -0.06
    POSITIVE LOGITS
    <>↵
    0.07
     hät
    0.06
     Gul
    0.06
    (sheet
    0.06
    vr
    0.06
    QUIRED
    0.06
     Rah
    0.06
    :image
    0.06
     во
    0.06
    pered
    0.06
    Activations Density 0.023%

    No Known Activations