© 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. 109750
    Prev
    Next
    INDEX
    Explanations

    Setting, defining, dictating

    np_max-act · gemini-2.0-flash

    This neuron activates on words used in formal specification or instruction contexts—terms that define, dictate, or describe how something works.

    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
    ,address
    -0.06
    วด
    -0.06
     Spirits
    -0.06
    UFF
    -0.06
     hashtable
    -0.06
    SPAN
    -0.06
    _Entity
    -0.06
    Storage
    -0.06
    	total
    -0.06
    sharing
    -0.06
    POSITIVE LOGITS
     determining
    0.07
     dictated
    0.07
     determines
    0.07
    (',',
    0.07
     dictate
    0.07
     تعیین
    0.07
     thích
    0.07
     bestimm
    0.07
     dictates
    0.07
    iddi
    0.07
    Activations Density 0.089%

    No Known Activations