© 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. 56241
    Prev
    Next
    INDEX
    Explanations

    pregnancy and fetal movement

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a pregnant baby’s or fetus’s movement (e.g. “baby is moving,” “fetal movement,” “quickening,” etc.).

    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
     �
    -0.07
    öl
    -0.07
     QE
    -0.06
     isVisible
    -0.06
     gorgeous
    -0.06
     bleeding
    -0.06
     lick
    -0.06
     Fate
    -0.06
    >>>>>>>
    -0.06
    694
    -0.06
    POSITIVE LOGITS
     activist
    0.06
    _display
    0.06
     destructor
    0.06
    �
    0.06
     waveform
    0.06
     hareket
    0.06
    Column
    0.06
     जगह
    0.06
     Ment
    0.06
    альні
    0.06
    Activations Density 0.005%

    No Known Activations