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. 130211
    Prev
    Next
    INDEX
    Explanations

    create

    np_max-act · gemini-2.0-flash

    The neuron activates on user requests phrased with the verb “create,” signaling a “create X” intent.

    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
     wants
    -0.06
    _symbol
    -0.06
     invoice
    -0.06
     docks
    -0.06
     리그
    -0.06
    707
    -0.06
    urrence
    -0.06
    าช
    -0.06
    Songs
    -0.06
    essment
    -0.06
    POSITIVE LOGITS
     datasource
    0.08
     enthusi
    0.08
    isRequired
    0.07
    >Nama
    0.06
    二二二二
    0.06
    ):
    0.06
     inspiration
    0.06
    ologically
    0.06
    DataContext
    0.06
     Seven
    0.06
    Activations Density 0.035%

    No Known Activations