© 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. 58768
    Prev
    Next
    INDEX
    Explanations

    diazepam

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of benzodiazepine drug names (e.g. diazepam and related compounds).

    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
    Column
    -0.07
     <->
    -0.06
     tally
    -0.06
     اب
    -0.06
     Really
    -0.06
     hip
    -0.06
     Glory
    -0.06
    Snow
    -0.06
     staffers
    -0.06
    POSITIVE LOGITS
     textures
    0.07
     muj
    0.06
     paj
    0.06
    john
    0.06
     proj
    0.06
     अल
    0.06
     मद
    0.06
    `.↵↵
    0.06
    :type
    0.06
    Automatic
    0.06
    Activations Density 0.010%

    No Known Activations