© 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. 68508
    Prev
    Next
    INDEX
    Explanations

    hardware

    np_max-act · gemini-2.0-flash

    The neuron is looking for mentions of hardware or physical tech (e.g. “hardware,” “hardware accelerator,” “factory‐grade metal”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical, research-oriented language, especially methodological descriptors and quantitative study details indicating analysis, optimization, scope, or novelty.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    095
    -0.07
    administration
    -0.07
     Wisdom
    -0.06
    ,target
    -0.06
     visualization
    -0.06
     GHz
    -0.06
     объект
    -0.06
    	cache
    -0.06
     mph
    -0.06
    	typ
    -0.06
    POSITIVE LOGITS
     зел
    0.07
    .fontSize
    0.07
    мати
    0.07
    BLACK
    0.07
     глав
    0.06
     Played
    0.06
     clap
    0.06
    CONN
    0.06
    ۲۸
    0.06
    antly
    0.06
    Activations Density 0.468%

    No Known Activations