Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 69113
    Prev
    Next
    INDEX
    Explanations

    Household items/utilities

    np_max-act · gemini-2.0-flash

    This neuron detects technical nouns referring to engineering or manufacturing components and equipment.

    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
    lime
    -0.07
     Çev
    -0.06
    ocular
    -0.06
    asd
    -0.06
    ека
    -0.06
     юрид
    -0.06
    took
    -0.06
    _par
    -0.06
    _Speed
    -0.06
    ultur
    -0.06
    POSITIVE LOGITS
     const
    0.06
    �
    0.06
     :↵↵↵↵
    0.06
     Photo
    0.06
    	gui
    0.06
     boolean
    0.06
     TypeError
    0.06
    Manifest
    0.06
     prog
    0.06
     gql
    0.06
    Activations Density 0.145%

    No Known Activations