Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55027
    Prev
    Next
    INDEX
    Explanations

    parseInt

    np_max-act · gemini-2.0-flash

    The neuron is detecting JavaScript module‐import statements (calls to require(…) or import statements).

    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
    .PRO
    -0.07
    .Sleep
    -0.07
    (re
    -0.07
    ibration
    -0.07
    �
    -0.06
     СП
    -0.06
    PRETTY
    -0.06
    )d
    -0.06
    .round
    -0.06
    рю
    -0.06
    POSITIVE LOGITS
     stalo
    0.08
     Daughter
    0.07
    ,默认
    0.07
    ژی
    0.07
    为什么
    0.07
    ispecies
    0.06
    Intent
    0.06
     unthinkable
    0.06
    ItemSelectedListener
    0.06
    ентів
    0.06
    Activations Density 0.018%

    No Known Activations