© 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. 91366
    Prev
    Next
    INDEX
    Explanations

    clinical

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “clinical.”

    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
    .putExtra
    -0.07
     spacer
    -0.07
    owie
    -0.06
    phabet
    -0.06
     Bast
    -0.06
    ARGE
    -0.06
     Barbar
    -0.06
    403
    -0.06
     TER
    -0.06
    ecessarily
    -0.06
    POSITIVE LOGITS
     Clinical
    0.13
     clinical
    0.12
    Clinical
    0.12
     Clinic
    0.11
     Clin
    0.10
     clinicians
    0.10
     clinic
    0.10
    clinical
    0.09
     klin
    0.09
     clin
    0.09
    Activations Density 0.018%

    No Known Activations