© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92579
    Prev
    Next
    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash

    The neuron is picking out the key Korean content words in an official municipal announcement—especially terms naming citizens (“용인시민”), documents (“주민등록증”), and congratulatory/supportive items (“축하카드,” “귀감,” “응원”)—that structure the formal congratulatory message.

    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
    protocol
    -0.07
    _PCIE
    -0.06
     wrath
    -0.06
    )?;↵
    -0.06
    Nevertheless
    -0.06
     Cass
    -0.06
     ald
    -0.06
    .seq
    -0.06
    degree
    -0.06
     belongings
    -0.06
    POSITIVE LOGITS
     apis
    0.06
    ']]],↵
    0.06
    Zoom
    0.06
    अ
    0.06
     hava
    0.06
     listened
    0.06
    edido
    0.06
    Wind
    0.06
     tog
    0.06
    Spoiler
    0.06
    Activations Density 0.063%

    No Known Activations