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. 130703
    Prev
    Next
    INDEX
    Explanations

    happy

    np_max-act · gemini-2.0-flash

    The neuron detects polite, positive “offer to help” language (e.g. “happy to …”).

    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
    °E
    -0.07
     File
    -0.07
     prefix
    -0.06
     cos
    -0.06
     install
    -0.06
     ov
    -0.06
    -прав
    -0.06
    /root
    -0.06
    "]=
    -0.06
     lear
    -0.06
    POSITIVE LOGITS
    ัตว
    0.07
     корот
    0.07
    .nasa
    0.06
     birlikte
    0.06
     satın
    0.06
     다양한
    0.06
     نحوه
    0.06
    ↵      ↵
    0.06
     треть
    0.06
    ीदव
    0.06
    Activations Density 0.008%

    No Known Activations