© 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. 54288
    Prev
    Next
    INDEX
    Explanations

    digital

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of digital or virtual currencies (e.g., “digital,” “cryptocurrency,” “currency”).

    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
    ư
    -0.06
    Write
    -0.06
     coke
    -0.06
     Supplements
    -0.06
    imens
    -0.06
     fund
    -0.06
     concerts
    -0.06
    不好
    -0.06
    	RE
    -0.06
    enou
    -0.06
    POSITIVE LOGITS
     possono
    0.07
     Declarations
    0.07
     saddle
    0.06
     EVP
    0.06
    .cycle
    0.06
     ger
    0.06
    	cv
    0.06
    loub
    0.06
    >',
    0.06
    Land
    0.06
    Activations Density 0.005%

    No Known Activations