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

    Neuronpedia

    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. 91374
    Prev
    Next
    INDEX
    Explanations

    travel destinations

    np_max-act · gemini-2.0-flash

    The neuron is highly responsive to proper-place names—especially travel-destination names like “Scotland,” “Hawaii,” or “Andorra”—in user prompts.

    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
    aid
    -0.07
    اعي
    -0.06
     حيث
    -0.06
    <Option
    -0.06
    DataMember
    -0.06
    asper
    -0.06
    λού
    -0.06
    Tim
    -0.06
     Ku
    -0.06
    016
    -0.06
    POSITIVE LOGITS
    =row
    0.07
     incent
    0.07
    302
    0.06
    -quarter
    0.06
     hukuk
    0.06
     sau
    0.06
     hmot
    0.06
    -hero
    0.06
     WRONG
    0.06
    _LSB
    0.06
    Activations Density 0.064%

    No Known Activations