© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73724
    Prev
    Next
    INDEX
    Explanations

    uintptr

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literal tokens (the numbers in the “uintptr(<number>)” syscall call arguments).

    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
    Les
    -0.07
    ★
    -0.06
    سد
    -0.06
     LogManager
    -0.06
    _given
    -0.06
     دوم
    -0.06
    LAT
    -0.06
     Doom
    -0.06
    (in
    -0.06
     kot
    -0.06
    POSITIVE LOGITS
    depth
    0.08
     uintptr
    0.07
    HTTP
    0.07
    _attr
    0.07
     stark
    0.07
     break
    0.07
     INTERRUPTION
    0.06
     ادبی
    0.06
    Monthly
    0.06
     мик
    0.06
    Activations Density 0.000%

    No Known Activations