© 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. 109080
    Prev
    Next
    INDEX
    Explanations

    information data

    np_max-act · gemini-2.0-flash

    The neuron detects instructional prompts asking to “extract the information” (i.e. directives to pull out details).

    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
     Angiosper
    -0.08
    ETING
    -0.07
    ьер
    -0.07
    Separator
    -0.06
    	Game
    -0.06
    نگ
    -0.06
     �
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
     結
    -0.06
    Settings
    -0.06
    POSITIVE LOGITS
     wanted
    0.07
     свого
    0.06
     лес
    0.06
     downloading
    0.06
    uyệ
    0.06
     Cheap
    0.06
     drains
    0.06
     Allied
    0.06
     cheap
    0.06
     dodge
    0.06
    Activations Density 0.038%

    No Known Activations