Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 84717
    Prev
    Next
    INDEX
    Explanations

    involved

    np_max-act · gemini-2.0-flash

    This neuron activates on Portuguese words, i.e. it detects text in Portuguese.

    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
     Bapt
    -0.07
    +"/"+
    -0.06
    Chron
    -0.06
    socket
    -0.06
     omega
    -0.06
     Tennis
    -0.06
    层
    -0.06
     heats
    -0.06
    cccc
    -0.06
    ibilidade
    -0.06
    POSITIVE LOGITS
    	actor
    0.06
    рав
    0.06
     deste
    0.06
    .gson
    0.06
    .setTo
    0.06
    форма
    0.06
     ingredient
    0.06
     ση
    0.06
    .paper
    0.06
    .phoneNumber
    0.06
    Activations Density 0.021%

    No Known Activations