© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44358
    Prev
    Next
    INDEX
    Explanations

    commas and "and"

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot ingredient names and cooking‐method words in menu or recipe descriptions.

    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
    	K
    -0.08
     summaries
    -0.07
    _employee
    -0.07
     Monterey
    -0.07
    AccountId
    -0.06
     intimate
    -0.06
    imator
    -0.06
     Dor
    -0.06
     tomatoes
    -0.06
    customers
    -0.06
    POSITIVE LOGITS
     kunne
    0.06
     geopolitical
    0.06
     '{@
    0.06
    .textField
    0.06
     nær
    0.06
    ỗng
    0.06
    λεύ
    0.06
     seiz
    0.06
     실�
    0.06
    úa
    0.06
    Activations Density 0.022%

    No Known Activations