© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 17516
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    Whether the text is the model/assistant's generated response (i.e., tokens from assistant output).

    oai_token-act-pair · gpt-5-miniTriggered 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
     trendy
    -0.07
    <message
    -0.06
    ้ำ
    -0.06
    INNER
    -0.06
    FontSize
    -0.06
    Tac
    -0.06
    roring
    -0.06
     فراهم
    -0.06
    954
    -0.06
     TensorFlow
    -0.06
    POSITIVE LOGITS
     ______
    0.06
     Autos
    0.06
     Invoice
    0.06
    Perform
    0.06
    _prof
    0.06
     nominee
    0.06
     quarters
    0.06
    _queue
    0.06
    ✔
    0.06
    Carol
    0.06
    Activations Density 0.103%

    No Known Activations