© 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. 128820
    Prev
    Next
    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash

    This neuron detects Jupyter notebook JSON structure tokens—e.g. the keys like “cell”, “_type”, “markdown”, “source”, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     eerste
    -0.07
    так
    -0.07
     worship
    -0.07
     chalk
    -0.06
     Hick
    -0.06
     organizational
    -0.06
     keys
    -0.06
    Pick
    -0.06
     陳
    -0.06
     oggi
    -0.06
    POSITIVE LOGITS
    �
    0.06
    ματα
    0.06
    polation
    0.06
    )},↵
    0.06
     -->↵↵
    0.06
    '),
    0.06
    备
    0.06
    ريل
    0.06
     direccion
    0.06
    "))↵↵
    0.06
    Activations Density 0.002%

    No Known Activations