© 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. 13687
    Prev
    Next
    INDEX
    Explanations

    organizations, sports, seasons

    np_max-act · gemini-2.0-flash

    The neuron responds to structural or metadata labels (e.g. section headings, infobox fields, and category titles) rather than ordinary content words.

    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
    雄
    -0.08
    Firebase
    -0.07
    भग
    -0.06
    Drag
    -0.06
    alternative
    -0.06
    .mov
    -0.06
     manifest
    -0.06
     jsonArray
    -0.06
    علام
    -0.06
    rosso
    -0.06
    POSITIVE LOGITS
     kW
    0.06
     이어
    0.06
     Mia
    0.06
     Nhân
    0.06
     Weiter
    0.06
    fter
    0.06
    攻击
    0.06
    ีท
    0.06
     glaring
    0.06
     intricate
    0.06
    Activations Density 0.041%

    No Known Activations