© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126893
    Prev
    Next
    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of a substance’s protective or inhibitory biological effects (e.g. “protects,” “protective activity,” studies showing reduced risk) in a scientific context.

    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
     Julien
    -0.07
     Seymour
    -0.07
    Show
    -0.06
    512
    -0.06
    σή
    -0.06
     deceive
    -0.06
    ську
    -0.06
     Ashton
    -0.06
     \""
    -0.06
    存于
    -0.06
    POSITIVE LOGITS
    ritable
    0.07
    avel
    0.06
     знач
    0.06
    EmailAddress
    0.06
    	KEY
    0.06
     Nel
    0.06
     summons
    0.06
     incess
    0.06
    (sample
    0.06
     conventional
    0.06
    Activations Density 0.257%

    No Known Activations