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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130190
    Prev
    Next
    INDEX
    Explanations

    Business and economics

    np_max-act · gemini-2.0-flash

    The neuron responds to words about productivity, efficiency, or enabling smooth, convenient operations.

    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
    415
    -0.07
     gems
    -0.06
    ORMAL
    -0.06
    	items
    -0.06
     تی
    -0.06
     Slate
    -0.06
     İz
    -0.06
    otch
    -0.06
    tyard
    -0.06
    \
    -0.06
    POSITIVE LOGITS
    mj
    0.07
     Occupation
    0.06
     miss
    0.06
     Brazil
    0.06
    vědom
    0.06
     EMPTY
    0.06
     remember
    0.06
     Brazilian
    0.06
     Kon
    0.06
     agosto
    0.06
    Activations Density 0.124%

    No Known Activations