© 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. 56101
    Prev
    Next
    INDEX
    Explanations

    bookbinding

    np_max-act · gemini-2.0-flash

    descriptions of book formats and conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of a book’s physical format or binding type (e.g., “Paperback,” “Hardcover”).

    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
     віт
    -0.07
     didSelectRowAtIndexPath
    -0.07
    	mat
    -0.06
    scene
    -0.06
     sensors
    -0.06
    射
    -0.06
    Watching
    -0.06
    engine
    -0.06
    EINVAL
    -0.06
     λέ
    -0.06
    POSITIVE LOGITS
    jpg
    0.07
     alarak
    0.07
    commons
    0.07
    prehensive
    0.07
     nhanh
    0.06
    toDouble
    0.06
     algunas
    0.06
    eways
    0.06
     Jahres
    0.06
     locals
    0.06
    Activations Density 0.002%

    No Known Activations