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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 68766
    Prev
    Next
    INDEX
    Explanations

    allergy

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of allergies or allergic reactions—especially references to peanut (and other nut) allergies.

    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
     以
    -0.07
    й
    -0.06
     春
    -0.06
     Dump
    -0.06
     Yamaha
    -0.06
    uler
    -0.06
    าะ
    -0.06
     discomfort
    -0.06
    Star
    -0.06
    -La
    -0.06
    POSITIVE LOGITS
     Veg
    0.07
    -born
    0.07
    fruit
    0.07
     catering
    0.06
     =~
    0.06
    ediği
    0.06
    ndern
    0.06
     BIG
    0.06
     получить
    0.06
    )sender
    0.06
    Activations Density 0.002%

    No Known Activations