© 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. 56390
    Prev
    Next
    INDEX
    Explanations

    literature search terms

    np_max-act · gemini-2.0-flash

    This neuron activates on terms and phrases describing literature‐search methodology (e.g., database names and search‐strategy wording).

    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
    존
    -0.07
    ObjectId
    -0.07
    家族
    -0.07
    두
    -0.06
    班
    -0.06
     PUBLIC
    -0.06
     Report
    -0.06
    Gender
    -0.06
    ET
    -0.06
     sabotage
    -0.06
    POSITIVE LOGITS
    isateur
    0.07
     stál
    0.06
    (off
    0.06
     Brewery
    0.06
    married
    0.06
     sensit
    0.06
    jQuery
    0.06
    Accordion
    0.06
     Agr
    0.06
     ś
    0.06
    Activations Density 0.006%

    No Known Activations