Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85895
    Prev
    Next
    INDEX
    Explanations

    Today

    np_max-act · gemini-2.0-flash

    The neuron responds to date/time indicator words in the system header, e.g. “Today,” “Date,” or month abbreviations like “Jul.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    text discussing the impact of technology on traditional forms of media.

    oai_token-act-pair · gpt-4o-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
     Carter
    -0.07
     har
    -0.07
     черв
    -0.07
     whiskey
    -0.06
     filmer
    -0.06
    parser
    -0.06
     flowers
    -0.06
     cms
    -0.06
    是在
    -0.06
    Har
    -0.06
    POSITIVE LOGITS
    getType
    0.06
    nome
    0.06
    atisfaction
    0.06
     BOT
    0.06
     Coupe
    0.06
     readFile
    0.06
    whereIn
    0.06
     volcanic
    0.06
     pagan
    0.06
    (outputs
    0.06
    Activations Density 0.046%

    No Known Activations