© 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. 76729
    Prev
    Next
    INDEX
    Explanations

    不

    np_max-act · gemini-2.0-flash

    polite phrases typically used in business communication.

    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
     MVC
    -0.07
     proven
    -0.07
    DN
    -0.07
     قن
    -0.07
    -cell
    -0.07
    ها
    -0.07
    urma
    -0.07
     HD
    -0.07
     검색
    -0.07
     Chrome
    -0.07
    POSITIVE LOGITS
    ，不
    0.10
     不
    0.09
    不
    0.09
    お
    0.09
    ับความ
    0.08
     disagrees
    0.08
    。不
    0.08
     tidak
    0.08
     ความ
    0.08
     상
    0.07
    Activations Density 0.016%

    No Known Activations