© 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. 15-RESID-POST-AA
    6. 104860
    Prev
    Next
    INDEX
    Explanations

    code, cache information

    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
    quo
    -0.06
    隆
    -0.06
    πισ
    -0.06
     useRouter
    -0.06
    enery
    -0.06
    908
    -0.06
    713
    -0.06
    accessible
    -0.06
     redefine
    -0.06
    ooter
    -0.06
    POSITIVE LOGITS
    Particles
    0.07
     исслед
    0.07
     Watch
    0.07
     envelope
    0.07
    |↵
    0.07
     treatment
    0.06
    )
    ↵
    0.06
     Rise
    0.06
    Network
    0.06
     covenant
    0.06
    Activations Density 0.000%

    No Known Activations