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. 40670
    Prev
    Next
    INDEX
    Explanations

    growing

    np_max-act · gemini-2.0-flash

    Neuron 4 spots mentions of growth, especially the words “growth” or “growing” used to describe increasing trends or markets.

    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
    íř
    -0.08
    Warnings
    -0.07
    793
    -0.07
     dán
    -0.07
    /tos
    -0.07
    \Storage
    -0.06
     místa
    -0.06
     Hermes
    -0.06
    ウィ
    -0.06
     idea
    -0.06
    POSITIVE LOGITS
     aspiring
    0.06
    '){
    ↵
    0.06
     Crescent
    0.06
     PH
    0.06
     basket
    0.06
     baj
    0.06
     booming
    0.06
    author
    0.06
     prosper
    0.06
     tail
    0.06
    Activations Density 0.013%

    No Known Activations