© 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. 30704
    Prev
    Next
    INDEX
    Explanations

    scientific and biological topics

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on the specialized biological term “erythroblastic,” i.e. words containing the root “erythroblast.”

    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
    烟
    -0.07
    fuck
    -0.07
    .ac
    -0.06
     Firearms
    -0.06
    оит
    -0.06
     мест
    -0.06
     роз
    -0.06
    ар
    -0.06
     iar
    -0.06
     rubbed
    -0.06
    POSITIVE LOGITS
     dolay
    0.07
     عرب
    0.07
     watched
    0.07
     simil
    0.07
    ятель
    0.06
    userInfo
    0.06
    (api
    0.06
    Stats
    0.06
    (null
    0.06
    createClass
    0.06
    Activations Density 0.407%

    No Known Activations