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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    6. 112219
    Prev
    Next
    INDEX
    Explanations

    carriers

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     front
    -0.07
     politic
    -0.07
     ([
    -0.07
     walk
    -0.06
    [str
    -0.06
     핵
    -0.06
    �
    -0.06
    크기
    -0.06
     Yorker
    -0.06
     Front
    -0.06
    POSITIVE LOGITS
     تلك
    0.07
     enter
    0.07
     Btn
    0.06
    ubs
    0.06
    steps
    0.06
     berth
    0.06
    /session
    0.06
    arParams
    0.06
    erglass
    0.06
     ****************************************************************************
    0.06
    Activations Density 0.249%

    No Known Activations