© 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. 92347
    Prev
    Next
    INDEX
    Explanations

    Sentence starting with "It's"

    np_max-act · gemini-2.0-flash

    The neuron activates on temporal expressions—mentions of times of day, dates, years, or durations.

    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
    itest
    -0.07
     Explore
    -0.07
     Data
    -0.06
     LDL
    -0.06
     records
    -0.06
     getBy
    -0.06
     prosecute
    -0.06
     unified
    -0.06
    ]byte
    -0.06
     контак
    -0.06
    POSITIVE LOGITS
     Alma
    0.07
    ند
    0.06
    Runner
    0.06
     زیبا
    0.06
    still
    0.06
     都
    0.06
     hry
    0.06
     eq
    0.06
    _QUESTION
    0.06
     dang
    0.06
    Activations Density 0.049%

    No Known Activations