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. 73116
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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
     Target
    -0.07
     visibility
    -0.06
    eping
    -0.06
    change
    -0.06
     ActiveSupport
    -0.06
    osten
    -0.06
    initial
    -0.06
    sar
    -0.06
     Peoples
    -0.06
     CN
    -0.06
    POSITIVE LOGITS
    렇
    0.06
    ้าก
    0.06
    BUM
    0.06
    ="@
    0.06
     proclaimed
    0.06
     FactoryGirl
    0.06
    Delete
    0.06
    .LINE
    0.06
    .Ad
    0.06
    мон
    0.06
    Activations Density 0.058%

    No Known Activations