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. 378
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (especially floating-point constants) in code.

    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
     Laboratories
    -0.07
     chants
    -0.07
    /all
    -0.06
     ترتیب
    -0.06
    hevik
    -0.06
    _accuracy
    -0.06
    Testing
    -0.06
     pillow
    -0.06
     interfaces
    -0.06
    (summary
    -0.06
    POSITIVE LOGITS
    нар
    0.06
     STDMETHOD
    0.06
     tego
    0.06
     реє
    0.06
     nuestra
    0.06
     �
    0.06
     std
    0.06
     дир
    0.05
     داشته
    0.05
    _DELETED
    0.05
    Activations Density 0.018%

    No Known Activations