© 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. 110090
    Prev
    Next
    INDEX
    Explanations

    Open bracket

    np_max-act · gemini-2.0-flash

    The neuron activates on bracketed numeric citations (e.g. “[1]”, “[2007]”) in the text.

    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
    ije
    -0.06
    สมบ
    -0.06
    URRENT
    -0.06
    pection
    -0.06
    ()>
    -0.06
    .AUTO
    -0.06
     Kabul
    -0.06
    بش
    -0.06
     StObject
    -0.06
    .pool
    -0.06
    POSITIVE LOGITS
     Relationship
    0.07
    かい
    0.07
     Georg
    0.06
     factions
    0.06
    ैस
    0.06
    =temp
    0.06
    _agent
    0.06
    DlgItem
    0.06
    impl
    0.06
    ۱۹۸
    0.06
    Activations Density 0.003%

    No Known Activations