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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102288
    Prev
    Next
    INDEX
    Explanations

    references and codes

    np_max-act · gemini-2.0-flash

    tokens typical of scientific/medical article formatting — section headings, reference/citation markers, and numeric values/measurements.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     за
    -0.07
    ्ड
    -0.07
     containing
    -0.06
     unions
    -0.06
    liers
    -0.06
    讨
    -0.06
    ogh
    -0.06
     ナ
    -0.06
    "But
    -0.06
    otypes
    -0.06
    POSITIVE LOGITS
     sách
    0.07
     AppleWebKit
    0.06
     artikel
    0.06
    ()},
    0.06
    Recovered
    0.06
    WhiteSpace
    0.06
     iPad
    0.06
     Monster
    0.06
     artır
    0.06
     userInput
    0.06
    Activations Density 0.304%

    No Known Activations