© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23115
    Prev
    Next
    INDEX
    Explanations

    "as the name suggests"

    np_max-act · gemini-2.0-flash

    information related to insurance policies.

    oai_token-act-pair · gpt-4o-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
     font
    -0.07
    voje
    -0.06
    وجد
    -0.06
    ti
    -0.06
    ूह
    -0.06
     &___
    -0.06
    .DE
    -0.06
     míst
    -0.06
     TResult
    -0.06
     Dairy
    -0.06
    POSITIVE LOGITS
    ند
    0.07
    лях
    0.06
     DHCP
    0.06
     Bonds
    0.06
     Ident
    0.06
     आकर
    0.06
    Sidebar
    0.06
    inator
    0.06
    bak
    0.06
     speculation
    0.06
    Activations Density 0.021%

    No Known Activations