© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56710
    Prev
    Next
    INDEX
    Explanations

    academic/technical context

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on capitalized multiword names and titles (e.g. “Operation Potomac,” “Triple Bottom Line,” “PHP date() function,” “Michael Porter,” “Annapurna by Maurice Herzog”), i.e. tokens within bibliographic/citation-style references and named entities.

    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
    thro
    -0.06
    DonaldTrump
    -0.06
     війни
    -0.06
    (undefined
    -0.06
     đẳng
    -0.06
     HomeController
    -0.06
     ČR
    -0.06
     Exclusive
    -0.06
     영국
    -0.06
    تو
    -0.06
    POSITIVE LOGITS
     Nude
    0.06
     Wil
    0.06
     Walter
    0.06
     Winchester
    0.06
    ction
    0.06
     Lawrence
    0.06
    VEN
    0.06
    PEND
    0.06
     Containers
    0.06
     –↵
    0.06
    Activations Density 0.043%

    No Known Activations