© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52830
    Prev
    Next
    INDEX
    Explanations

    Software

    np_max-act · gemini-2.0-flash

    keywords related to software licensing and permissions.

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

    The neuron is strongly triggered by occurrences of the word “Software” in license‐header boilerplate.

    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
    (cn
    -0.07
     الك
    -0.06
    (items
    -0.06
     Kon
    -0.06
    ประช
    -0.06
     pouring
    -0.06
    mons
    -0.06
    ậm
    -0.06
     yếu
    -0.06
     keyword
    -0.06
    POSITIVE LOGITS
     총
    0.06
     STDMETHODCALLTYPE
    0.06
    erb
    0.06
     shimmer
    0.06
     MMI
    0.06
     초기
    0.06
    年度
    0.06
    (util
    0.06
    .UP
    0.06
    CKET
    0.06
    Activations Density 0.000%

    No Known Activations