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. 85941
    Prev
    Next
    INDEX
    Explanations

    thrift

    np_max-act · gemini-2.0-flash

    The neuron activates on references to thrift shopping and second-hand clothing stores.

    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
     Logging
    -0.07
    もっと
    -0.07
     چیز
    -0.07
    顾
    -0.07
     bisa
    -0.07
     داشته
    -0.06
    检测
    -0.06
     전
    -0.06
     CreateUser
    -0.06
    _summary
    -0.06
    POSITIVE LOGITS
     eclectic
    0.07
    phil
    0.06
    ünd
    0.06
     pci
    0.06
     lesbian
    0.06
     vyšší
    0.06
    eties
    0.06
     яких
    0.06
     Pedro
    0.06
     BUFF
    0.06
    Activations Density 0.029%

    No Known Activations