© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12507
    Prev
    Next
    INDEX
    Explanations

    Jar

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of jars (i.e. the word “jar” or jar-based containers).

    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
     bố
    -0.07
     비밀
    -0.07
    Campo
    -0.07
     Techn
    -0.07
    uality
    -0.07
     Sport
    -0.07
    電視
    -0.07
     propulsion
    -0.07
    Tele
    -0.07
    CPF
    -0.07
    POSITIVE LOGITS
     Jar
    0.14
     jar
    0.14
    jar
    0.11
     jars
    0.11
    Jar
    0.11
    jam
    0.07
    Jam
    0.07
    .jar
    0.07
    cker
    0.07
     lar
    0.07
    Activations Density 0.005%

    No Known Activations