© 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. 109788
    Prev
    Next
    INDEX
    Explanations

    javascript arrays and numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on references to JavaScript’s Array prototype methods (e.g. “.array” followed by “.find,” “.slice,” “.sort,” “.lastIndexOf,” 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
     ustanovení
    -0.07
    mium
    -0.06
     del
    -0.06
     Choose
    -0.06
     Zodiac
    -0.06
     fung
    -0.06
    PasswordEncoder
    -0.06
    (...)↵
    -0.06
    ughters
    -0.06
    ewart
    -0.06
    POSITIVE LOGITS
     wage
    0.07
    障
    0.06
    imageUrl
    0.06
    атар
    0.06
     واب
    0.06
     trạng
    0.06
    mods
    0.06
    álně
    0.06
    .ui
    0.06
    .Xna
    0.06
    Activations Density 0.005%

    No Known Activations