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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 101026
    Prev
    Next
    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash

    concepts related to optical communication technologies.

    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
    셔
    -0.07
     Charter
    -0.07
     Cycle
    -0.06
    AVE
    -0.06
    ้อน
    -0.06
     นาง
    -0.06
    duplicate
    -0.06
    ور
    -0.06
    ओ
    -0.06
     Guinness
    -0.06
    POSITIVE LOGITS
    首页
    0.08
     [~,
    0.07
     кому
    0.07
     birlikte
    0.07
    ้อง
    0.07
    ?$
    0.07
    	files
    0.07
    /lib
    0.06
     عملیات
    0.06
    lut
    0.06
    Activations Density 0.109%

    No Known Activations