© 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 EvalsExportsinterp-engineNEWAPI 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. 39138
    Prev
    Next
    INDEX
    Explanations

    Death

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect mentions of death or passing away (e.g., “passed,” “away,” “dying,” “let … go”).

    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
    ์
    -0.06
    容
    -0.06
    Bone
    -0.06
     steak
    -0.06
     сы
    -0.06
     обращ
    -0.06
    _be
    -0.06
     Cur
    -0.06
     brothers
    -0.06
    ,en
    -0.05
    POSITIVE LOGITS
     instagram
    0.08
     exemplary
    0.07
    void
    0.07
    Interface
    0.07
     GObject
    0.07
     blessed
    0.07
     dục
    0.07
    .IsChecked
    0.07
    continued
    0.07
    	pass
    0.06
    Activations Density 0.011%

    No Known Activations