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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130522
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (especially floating‐point numbers) in the 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
    世紀
    -0.07
     remarkably
    -0.07
    ienie
    -0.06
    ’ve
    -0.06
    тами
    -0.06
    amics
    -0.06
    ;:;:;:;:
    -0.06
     piè
    -0.06
     Wave
    -0.06
    _subject
    -0.06
    POSITIVE LOGITS
      ↵    ↵
    0.07
     opin
    0.07
     	   
    0.06
    nThe
    0.06
     συμπ
    0.06
    efault
    0.06
    áz
    0.06
    irect
    0.06
     сопров
    0.06
    ocoder
    0.06
    Activations Density 0.111%

    No Known Activations