© 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. 13695
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    The neuron activates on single‐digit numerals used as version or generation markers in technical specifications (e.g. “6” in Wi-Fi 6, “3” in USB 3.2 Gen 1).

    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
     totalCount
    -0.07
    cısı
    -0.07
    scheduled
    -0.07
    нин
    -0.07
    _DU
    -0.06
    seconds
    -0.06
    apesh
    -0.06
    lacağ
    -0.06
     /↵↵
    -0.06
    =C
    -0.06
    POSITIVE LOGITS
     ó
    0.06
     inserting
    0.06
     hemp
    0.06
    _hash
    0.06
     filtered
    0.06
     fearing
    0.06
     Org
    0.06
     Lib
    0.06
     suprem
    0.06
     Myst
    0.06
    Activations Density 0.002%

    No Known Activations