© 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. 599
    Prev
    Next
    INDEX
    Explanations

    world domination

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of formidable fictional forces or creatures (e.g. armies of terminators, dragons, lizard people).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    mentions of conquest, world domination, armies, or violent takeover (e.g., "take over the world", "army of terminators").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     kd
    -0.07
     raised
    -0.07
    unidad
    -0.06
     Estonia
    -0.06
    モン
    -0.06
     unveiled
    -0.06
    де
    -0.06
    016
    -0.06
    มอ
    -0.06
    MH
    -0.06
    POSITIVE LOGITS
     predicates
    0.07
    、
    0.06
    采用
    0.06
     Decrypt
    0.06
    ')==
    0.06
    Jul
    0.06
    .s
    0.06
     Scalars
    0.06
     phút
    0.06
    (""+
    0.06
    Activations Density 0.096%

    No Known Activations