© 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. 30113
    Prev
    Next
    INDEX
    Explanations

    signal

    np_max-act · gemini-2.0-flash

    The neuron fires on code tokens referring to signal‐handling, especially the “multiprocess_signals” module or similarly named signal‐management identifiers.

    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
    okud
    -0.07
    (tool
    -0.06
    EObject
    -0.06
     Keith
    -0.06
    від
    -0.06
     wash
    -0.06
    Occ
    -0.06
    /mark
    -0.06
     رفته
    -0.06
    ############
    -0.06
    POSITIVE LOGITS
    NdEx
    0.07
    incipal
    0.07
    kinci
    0.07
    _PRIVATE
    0.06
     gọi
    0.06
     sözleş
    0.06
     professional
    0.06
    _variables
    0.06
     Messages
    0.06
     scalable
    0.06
    Activations Density 0.004%

    No Known Activations