© 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. 90780
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    references to political scandals and controversies involving funding and honorariums.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on mentions of geographic locations (cities, countries, regions).

    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
     hookup
    -0.08
    Patrick
    -0.07
    Serial
    -0.06
    орг
    -0.06
    plans
    -0.06
    corr
    -0.06
    PAD
    -0.06
    的问题
    -0.06
    Boot
    -0.06
    كام
    -0.06
    POSITIVE LOGITS
     textbooks
    0.07
     SubLObject
    0.06
     trif
    0.06
     बढ
    0.06
     ded
    0.06
     làn
    0.06
     β
    0.06
     (↵↵
    0.06
     attract
    0.06
     Bắc
    0.06
    Activations Density 0.257%

    No Known Activations