© 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. 41299
    Prev
    Next
    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash

    terms related to acoustic properties in a space.

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

    This neuron detects definitional phrases—especially “is a … measure of,” “is defined as,” and similar constructions that introduce or explain a term.

    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
     patt
    -0.07
     pantry
    -0.06
    ترنت
    -0.06
    '))->
    -0.06
     PHONE
    -0.06
    媒体
    -0.06
    ΕΙΣ
    -0.06
     สำน
    -0.06
     Contracts
    -0.06
    etails
    -0.06
    POSITIVE LOGITS
    }_${
    0.07
     nije
    0.07
     نظام
    0.07
     مصر
    0.06
    _shell
    0.06
     "${
    0.06
    148
    0.06
    >Hello
    0.06
     recall
    0.06
     Colonel
    0.06
    Activations Density 0.117%

    No Known Activations