© 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
    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. 92411
    Prev
    Next
    INDEX
    Explanations

    /docker

    np_max-act · gemini-2.0-flash

    The neuron fires on code mentions of the Docker client/API—e.g. import paths, method names, endpoints, and config keys containing “docker.”

    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
     Slayer
    -0.07
     textView
    -0.06
     PLA
    -0.06
    (cc
    -0.06
    #a
    -0.06
    IndexOf
    -0.06
    ERICA
    -0.06
     노래
    -0.06
    /car
    -0.06
    .HandleFunc
    -0.06
    POSITIVE LOGITS
    (library
    0.07
     Tribal
    0.06
    untime
    0.06
    ultan
    0.06
    -white
    0.06
     architects
    0.06
     medicinal
    0.06
     sudo
    0.06
     رنگ
    0.06
     likewise
    0.06
    Activations Density 0.006%

    No Known Activations