© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 57357
    Prev
    Next
    INDEX
    Explanations

    Patients/Subjects

    np_max-act · gemini-2.0-flash

    This neuron activates on words that refer to study participants or cohorts (e.g., “patients,” “subjects,” “individuals”).

    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
    etadata
    -0.07
    Viewport
    -0.07
     Summary
    -0.06
     Combination
    -0.06
    .locations
    -0.06
     LOGGER
    -0.06
    truck
    -0.06
     upstairs
    -0.06
     serialVersionUID
    -0.06
     Securities
    -0.06
    POSITIVE LOGITS
    蕉
    0.07
     KY
    0.06
     Společ
    0.06
    fund
    0.06
    *"
    0.06
    ій
    0.06
     CIM
    0.06
    (png
    0.06
     характериз
    0.06
    _inode
    0.06
    Activations Density 0.029%

    No Known Activations