© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 20785
    Prev
    Next
    INDEX
    Explanations

    health in developing countries

    np_max-act · gemini-2.0-flash
    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
     Ket
    -0.06
    (shell
    -0.06
     خیابان
    -0.06
    ��
    -0.06
     ل
    -0.06
     kry
    -0.06
     giao
    -0.06
     trval
    -0.06
     alın
    -0.06
    frey
    -0.06
    POSITIVE LOGITS
     Emerging
    0.08
     developing
    0.07
    	↵↵↵
    0.07
     Inject
    0.07
    Reflect
    0.07
     Blend
    0.07
    UG
    0.06
     Spring
    0.06
     vibrant
    0.06
    ブ
    0.06
    Activations Density 0.009%

    No Known Activations