Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35807
    Prev
    Next
    INDEX
    Explanations

    race and ethnicity

    np_max-act · gemini-2.0-flash
    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
     arp
    -0.07
    Language
    -0.07
    Stock
    -0.06
    .stock
    -0.06
    习
    -0.06
    ils
    -0.06
     probation
    -0.06
     Jeb
    -0.06
    -Am
    -0.06
    ष
    -0.06
    POSITIVE LOGITS
    \core
    0.08
    .super
    0.07
    pageIndex
    0.07
     haystack
    0.07
     appBar
    0.07
    년에
    0.06
    させ
    0.06
    jes
    0.06
    igrationBuilder
    0.06
     Mö
    0.06
    Activations Density 0.013%

    No Known Activations