© 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. 126064
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    This neuron detects programming‐style syntax, especially JavaScript keywords and code tokens (e.g. “function,” “constructor,” “require,” braces, etc.)

    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
     він
    -0.06
     dubbed
    -0.06
     выбра
    -0.06
     nen
    -0.06
     сем
    -0.06
    @GeneratedValue
    -0.06
     maxLength
    -0.06
    _return
    -0.06
    .getWritableDatabase
    -0.06
     rr
    -0.06
    POSITIVE LOGITS
    ITA
    0.07
    .slice
    0.07
    Mini
    0.06
    ินด
    0.06
    따
    0.06
     ADDR
    0.06
    โจ
    0.06
     sám
    0.06
    ahoo
    0.06
     Instruments
    0.06
    Activations Density 0.008%

    No Known Activations