© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6742
    Prev
    Next
    INDEX
    Explanations

    business/economics

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric data—digits, decimals, percentages, and other quantitative measurements in the 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
     Phelps
    -0.06
     до
    -0.06
     बस
    -0.06
    basis
    -0.06
     imageView
    -0.06
     ||
    -0.06
    .vote
    -0.06
    APPED
    -0.06
     Govern
    -0.06
     desserts
    -0.06
    POSITIVE LOGITS
    281
    0.07
     centrif
    0.06
     آهنگ
    0.06
    .int
    0.06
    (木
    0.06
    .Fire
    0.06
    sizei
    0.06
    privation
    0.06
     вер
    0.06
     alb
    0.06
    Activations Density 0.033%

    No Known Activations