© 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. 127057
    Prev
    Next
    INDEX
    Explanations

    engineering devices/applications

    np_max-act · gemini-2.0-flash

    The neuron activates on technical terms that describe physical surfaces and their orientations (e.g. “surface,” “vertical,” “parallel”) in engineering patent text.

    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
    .statusCode
    -0.07
    ぶ
    -0.07
    kr
    -0.06
    casting
    -0.06
    .Place
    -0.06
     narrowly
    -0.06
    _ts
    -0.06
    инки
    -0.06
    Unchecked
    -0.06
    /src
    -0.06
    POSITIVE LOGITS
    嘛
    0.07
     سنة
    0.07
     sitio
    0.07
     undert
    0.06
     gobierno
    0.06
    _interface
    0.06
    ์↵↵
    0.06
    動
    0.06
     Επι
    0.06
     mejor
    0.06
    Activations Density 0.057%

    No Known Activations