© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 124656
    Prev
    Next
    INDEX
    Explanations

    FIFA video game

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    γι
    -0.07
    价
    -0.07
    Sim
    -0.06
     hen
    -0.06
     UTF
    -0.06
    'I
    -0.06
    比
    -0.06
    Mom
    -0.06
     Nurs
    -0.06
     prisons
    -0.06
    POSITIVE LOGITS
    ungi
    0.07
     govern
    0.07
    的情况
    0.06
     misconception
    0.06
     Serialization
    0.06
    ilip
    0.06
    (Console
    0.06
     설정
    0.06
    .BooleanField
    0.06
     incorporating
    0.06
    Activations Density 0.073%

    No Known Activations