© 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. 90826
    Prev
    Next
    INDEX
    Explanations

    domain extensions

    np_max-act · gemini-2.0-flash

    The neuron activates on fragments of web addresses—especially domain names and country-code top-level domains (e.g. “.com.br”, “.co.za”).

    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
     Kohana
    -0.07
    :async
    -0.07
    uptools
    -0.07
     hoàn
    -0.06
     HttpMethod
    -0.06
     Thorn
    -0.06
    Rod
    -0.06
    them
    -0.06
    g
    -0.06
    alyzer
    -0.06
    POSITIVE LOGITS
    .K
    0.07
    ヶ
    0.07
    ικα
    0.06
    .de
    0.06
    trak
    0.06
     ศ
    0.06
     vac
    0.06
    .ca
    0.06
     зн
    0.06
    (SQLException
    0.06
    Activations Density 0.011%

    No Known Activations