© 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. 88954
    Prev
    Next
    INDEX
    Explanations

    Background art descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects patent-style section headings (e.g. “Field of the Invention” or “Background Art”).

    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
    +"'
    -0.06
     area
    -0.06
     dot
    -0.06
     rivers
    -0.06
    _ui
    -0.06
    ("[%
    -0.06
    weep
    -0.06
     height
    -0.06
    字符串
    -0.06
     creek
    -0.06
    POSITIVE LOGITS
     Brendan
    0.07
    .compress
    0.07
     conhe
    0.07
    Gen
    0.07
    .ops
    0.06
    ентом
    0.06
    Edward
    0.06
    .program
    0.06
    _softmax
    0.06
    状况
    0.06
    Activations Density 0.009%

    No Known Activations