© 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. 11-RESID-POST-AA
    6. 31126
    Prev
    Next
    INDEX
    Explanations

    Disclaimer

    np_max-act · gemini-2.0-flash

    markers that indicate the assistant’s role or the beginning of an assistant/model response in a chat-style transcript.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     painfully
    -0.06
    Adds
    -0.06
     lên
    -0.06
    Uploader
    -0.06
     neby
    -0.06
     изуч
    -0.06
     sometimes
    -0.06
     واقع
    -0.06
    _loading
    -0.06
    ayload
    -0.06
    POSITIVE LOGITS
    ListItemText
    0.07
    Bluetooth
    0.07
    (HttpStatus
    0.07
    .SuppressLint
    0.06
     ister
    0.06
     nitrogen
    0.06
    _design
    0.06
    .TimeUnit
    0.06
     tow
    0.06
    forces
    0.06
    Activations Density 0.081%

    No Known Activations