© 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. 11-RESID-POST-AA
    6. 25687
    Prev
    Next
    INDEX
    Explanations

    Describing qualities

    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
    ollider
    -0.07
    athlon
    -0.06
     скры
    -0.06
     inline
    -0.06
    Wall
    -0.06
    목
    -0.06
     aka
    -0.06
     sito
    -0.06
    Gem
    -0.06
    ز
    -0.06
    POSITIVE LOGITS
     ALTER
    0.07
     Relatives
    0.06
     Prep
    0.06
     Ritch
    0.06
    лишком
    0.06
    =P
    0.06
    Coming
    0.06
    :P
    0.06
     Squad
    0.06
     inflammation
    0.06
    Activations Density 0.085%

    No Known Activations