© 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. 129655
    Prev
    Next
    INDEX
    Explanations

    sys

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the Python identifier “sys” (in import statements and attribute accesses).

    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
     handbook
    -0.07
    tor
    -0.07
     Nokia
    -0.06
    ASP
    -0.06
     manufacturer
    -0.06
     zboží
    -0.06
     keyword
    -0.06
     sizin
    -0.06
     decoding
    -0.06
     Bing
    -0.06
    POSITIVE LOGITS
     sys
    0.08
    .getConfig
    0.07
     Multiply
    0.07
    _false
    0.07
     contrib
    0.07
    HITE
    0.07
    IFORM
    0.06
    筑
    0.06
    .setAction
    0.06
    .blur
    0.06
    Activations Density 0.001%

    No Known Activations