© 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. 44217
    Prev
    Next
    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash

    elements related to visuals in film production.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects terms associated with production design and set decoration roles (e.g., “set,” “decorator,” “designer”).

    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
    vars
    -0.07
     turnover
    -0.06
    Functions
    -0.06
     Employer
    -0.06
    _pending
    -0.06
     pocket
    -0.06
     Simpsons
    -0.06
     pien
    -0.06
    Sir
    -0.06
     doz
    -0.06
    POSITIVE LOGITS
     Blanc
    0.08
     dropdown
    0.07
    ='<?
    0.07
    (['
    0.07
     pří
    0.06
    ียง
    0.06
    ํ
    0.06
     />↵
    0.06
    _ZONE
    0.06
     birisi
    0.06
    Activations Density 0.012%

    No Known Activations