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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130388
    Prev
    Next
    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash

    The neuron fires on expressions of affection or enjoyment—particularly occurrences of "love" (and its inflected forms) indicating positive sentiment.

    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
     contracting
    -0.07
    럴
    -0.07
    	cuda
    -0.06
    Dst
    -0.06
    dark
    -0.06
    pb
    -0.06
    ара
    -0.06
    sg
    -0.06
    _ip
    -0.06
     stretching
    -0.06
    POSITIVE LOGITS
     "%"
    0.07
     Perspectives
    0.07
     выступ
    0.07
     mới
    0.06
    larınız
    0.06
     yummy
    0.06
    对于
    0.06
     تج
    0.06
     budou
    0.06
    :“
    0.06
    Activations Density 0.058%

    No Known Activations