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. 85983
    Prev
    Next
    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash

    text related to rural life and community aspects.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates specifically on the word “fields” (in its natural‐landscape context).

    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
    azo
    -0.07
    acet
    -0.07
    (session
    -0.06
    /users
    -0.06
    ("\(
    -0.06
     We
    -0.06
     BT
    -0.06
     BP
    -0.06
    :[],↵
    -0.06
     Email
    -0.06
    POSITIVE LOGITS
     fields
    0.07
     Fields
    0.07
    ’S
    0.06
    ▏▏
    0.06
     категор
    0.06
     field
    0.06
    toHaveBeenCalled
    0.06
    čer
    0.06
    调用
    0.06
     secara
    0.06
    Activations Density 0.017%

    No Known Activations