© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110119
    Prev
    Next
    INDEX
    Explanations

    Interleukin-6 and chemical experiments

    np_max-act · gemini-2.0-flash

    The neuron activates on the names of specific burger toppings or ingredients.

    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
    _bool
    -0.06
     mse
    -0.06
    :href
    -0.06
     Excell
    -0.06
     lẫn
    -0.06
     Merrill
    -0.06
     район
    -0.06
     TextBox
    -0.06
    妃
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    adier
    0.07
    reating
    0.07
     společně
    0.06
    운동
    0.06
     polling
    0.06
     ADS
    0.06
    _PM
    0.06
    -non
    0.06
     fluent
    0.06
     slips
    0.06
    Activations Density 0.759%

    No Known Activations