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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128374
    Prev
    Next
    INDEX
    Explanations

    infrared

    np_max-act · gemini-2.0-flash

    The neuron fires on specialized astrophysics jargon—particularly terms referring to evolved stars (AGB/asymptotic giant branch), cosmic dust, and infrared observations.

    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
    _debug
    -0.07
     dışarı
    -0.07
    ouro
    -0.07
    .addObject
    -0.06
    .horizontal
    -0.06
     krij
    -0.06
    .tabPage
    -0.06
    kara
    -0.06
     ž
    -0.06
    	Message
    -0.06
    POSITIVE LOGITS
     Başkanı
    0.07
    icking
    0.07
     germ
    0.07
    apture
    0.07
    олю
    0.06
     Korea
    0.06
     Likely
    0.06
     oily
    0.06
     additional
    0.06
    空间
    0.06
    Activations Density 0.005%

    No Known Activations