© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38759
    Prev
    Next
    INDEX
    Explanations

    Craft

    np_max-act · gemini-2.0-flash

    This neuron detects the word “craft” (and its morphological variants like “crafting,” “crafted,” “craftsmanship,” etc.) in the text.

    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
    alendar
    -0.08
     minimize
    -0.08
     eye
    -0.08
     Governor
    -0.08
     no
    -0.07
     Nez
    -0.07
     NO
    -0.07
     nose
    -0.07
     Zero
    -0.07
    No
    -0.07
    POSITIVE LOGITS
     craft
    0.13
    Craft
    0.11
     Craft
    0.11
    craft
    0.10
     craftsm
    0.09
     crafting
    0.09
     Crawford
    0.09
     crafted
    0.09
     Crafts
    0.08
    fant
    0.08
    Activations Density 0.013%

    No Known Activations