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. 8568
    Prev
    Next
    INDEX
    Explanations

    gpio

    np_max-act · gemini-2.0-flash

    C programming constructs related to GPIO (General Purpose Input Output) device driver development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags any mention of GPIO (general-purpose I/O)—headers, functions, or structures—in code.

    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
     racket
    -0.07
     jeszcze
    -0.07
     uterus
    -0.06
    collection
    -0.06
    f
    -0.06
     np
    -0.06
     queues
    -0.06
     sharks
    -0.06
    -band
    -0.06
    [of
    -0.06
    POSITIVE LOGITS
    GPIO
    0.08
     GPIO
    0.08
    (GPIO
    0.08
    .GPIO
    0.07
    λλι
    0.07
     إل
    0.07
     gpio
    0.07
    يكي
    0.07
     dne
    0.07
     حالة
    0.06
    Activations Density 0.004%

    No Known Activations