© 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. 89067
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron activates on the curly‐brace expressions surrounding type names in JSDoc comments (i.e. the “{Type}” annotations).

    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
    >xpath
    -0.07
    İs
    -0.07
    adastrar
    -0.07
    r
    -0.07
     Ved
    -0.07
    clang
    -0.07
    사람
    -0.07
    _for
    -0.07
    输
    -0.06
    YC
    -0.06
    POSITIVE LOGITS
    (ListNode
    0.07
    .Components
    0.06
     कभ
    0.06
    екти
    0.06
     etree
    0.06
    .ones
    0.05
    كي
    0.05
     caveat
    0.05
    entina
    0.05
    关于
    0.05
    Activations Density 0.001%

    No Known Activations