© 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. 90600
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on code tokens that denote function or method invocations—specifically the parentheses and the identifier immediately before them.

    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
     себе
    -0.07
    avid
    -0.07
    _canvas
    -0.07
    nty
    -0.07
    Simon
    -0.06
    Daniel
    -0.06
    wat
    -0.06
     executable
    -0.06
     Abraham
    -0.06
    linkplain
    -0.06
    POSITIVE LOGITS
     lingerie
    0.07
    ,《
    0.06
    、日本
    0.06
    ecká
    0.06
    赏
    0.06
     ComboBox
    0.06
     şekil
    0.06
    рас
    0.06
    (jButton
    0.05
    (i
    0.05
    Activations Density 0.072%

    No Known Activations