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. 40435
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects phrases expressing spatial proximity (e.g., “next to,” “adjacent to,” “attached to,” “situated next 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
    ":[
    -0.07
     boat
    -0.07
     Determine
    -0.07
    جد
    -0.07
    Pipeline
    -0.07
     TY
    -0.07
     fights
    -0.06
    وية
    -0.06
    _mp
    -0.06
    Logger
    -0.06
    POSITIVE LOGITS
     demol
    0.07
    ्छ
    0.06
     �
    0.06
    .jsx
    0.06
    _imag
    0.06
     altogether
    0.06
    озя
    0.06
     ear
    0.06
     欧美
    0.06
    pressive
    0.06
    Activations Density 0.015%

    No Known Activations