© 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. 30853
    Prev
    Next
    INDEX
    Explanations

    Questions and excerpts

    np_max-act · gemini-2.0-flash

    This neuron detects the introductory “In …,” prepositional phrase that often begins formal sentences or section headings (e.g. “In recent years,” or “In this section,”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phrases related to the impact of conditions on overall well-being.

    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
    unched
    -0.07
    	Button
    -0.06
    	model
    -0.06
    ‌گذ
    -0.06
     Parsing
    -0.06
    (),'
    -0.06
     desper
    -0.06
    oust
    -0.06
    	matrix
    -0.06
    etrics
    -0.06
    POSITIVE LOGITS
    .setBackground
    0.06
    Regardless
    0.06
     Eggs
    0.06
    (BASE
    0.06
     hitter
    0.06
    (:,:,
    0.06
     Neptune
    0.06
    Park
    0.06
     shimmer
    0.05
    uuml
    0.05
    Activations Density 0.059%

    No Known Activations