© 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. 44355
    Prev
    Next
    INDEX
    Explanations

    siege

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of military sieges, specifically the token “siege.”

    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
    mega
    -0.07
    .answer
    -0.07
    “But
    -0.06
    cluster
    -0.06
    vel
    -0.06
    girls
    -0.06
     stupid
    -0.06
    anes
    -0.06
     использовать
    -0.06
     transmitter
    -0.06
    POSITIVE LOGITS
     siege
    0.09
     Siege
    0.07
     ><?
    0.07
    援
    0.07
     шт
    0.07
    ์ด
    0.06
     guarding
    0.06
    �
    0.06
     iletişim
    0.06
     рекоменда
    0.06
    Activations Density 0.004%

    No Known Activations