© 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. 91268
    Prev
    Next
    INDEX
    Explanations

    luteal activity

    np_max-act · gemini-2.0-flash

    The neuron fires on any occurrence of the “lute” root in hormonal terms—e.g. “luteal,” “luteolysis,” “luteinizing,” “corpus luteum”—marking references to lute‐related processes.

    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
     HS
    -0.07
    érer
    -0.07
    unread
    -0.06
    ámara
    -0.06
     mars
    -0.06
    曜日
    -0.06
     useSelector
    -0.06
    Rep
    -0.06
    Native
    -0.06
    article
    -0.06
    POSITIVE LOGITS
    (baseUrl
    0.06
     Sgt
    0.06
     эта
    0.06
    ulty
    0.06
     LIFE
    0.06
    [e
    0.06
    提高
    0.06
     Cert
    0.06
     Creat
    0.06
    (Label
    0.06
    Activations Density 0.001%

    No Known Activations