© 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. 13838
    Prev
    Next
    INDEX
    Explanations

    pregnancy

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to pregnancy (e.g., “pregnancy,” “pregnant,” “trimest­er”).

    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
    enterprise
    -0.08
     ба
    -0.07
     Kim
    -0.06
    ButtonType
    -0.06
    	param
    -0.06
    .Initial
    -0.06
    Connected
    -0.06
    Constraint
    -0.06
    .Italic
    -0.06
    _BUS
    -0.06
    POSITIVE LOGITS
    άλι
    0.07
    0.07
    .io
    0.06
    ール
    0.06
    riere
    0.06
    .lot
    0.06
     clearTimeout
    0.06
    Guest
    0.06
     scrimmage
    0.06
     ansible
    0.06
    Activations Density 0.012%

    No Known Activations