© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29816
    Prev
    Next
    INDEX
    Explanations

    uname

    np_max-act · gemini-2.0-flash

    The neuron fires on shell‐script snippets that use the uname command—especially uname -m—to query the machine’s architecture.

    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
    	nil
    -0.07
     clearly
    -0.07
     Jos
    -0.06
    .Di
    -0.06
     req
    -0.06
    ox
    -0.06
    _REQUEST
    -0.06
     подоб
    -0.06
    _epoch
    -0.06
    .dt
    -0.06
    POSITIVE LOGITS
    _converter
    0.07
     MPC
    0.06
     เคร
    0.06
    erdem
    0.06
     Spring
    0.06
    ="<?=$
    0.06
    /ar
    0.06
    VENTORY
    0.06
    очные
    0.06
     asm
    0.06
    Activations Density 0.002%

    No Known Activations