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. 84475
    Prev
    Next
    INDEX
    Explanations

    worries

    np_max-act · gemini-2.0-flash

    This neuron activates on words expressing worry, care, stress, or emotional trouble.

    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
    手
    -0.07
     ner
    -0.07
     leer
    -0.07
    []
    ↵
    -0.06
     professionally
    -0.06
     <|
    -0.06
    Flying
    -0.06
     thao
    -0.06
    atom
    -0.06
    lico
    -0.06
    POSITIVE LOGITS
     erotische
    0.07
    percent
    0.07
     worries
    0.06
    _remote
    0.06
    -purple
    0.06
    .tencent
    0.06
     Stanford
    0.06
     menggunakan
    0.06
    _atual
    0.06
     toprak
    0.06
    Activations Density 0.023%

    No Known Activations