© 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. 18601
    Prev
    Next
    INDEX
    Explanations

    processes, functionality, failures

    np_max-act · gemini-2.0-flash

    commands related to forcefully terminating processes in Unix-based systems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron specifically fires on the phrase “running smoothly.”

    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
    	all
    -0.07
     oats
    -0.06
     hộp
    -0.06
    PDF
    -0.06
    lg
    -0.06
    .AreEqual
    -0.06
     اي
    -0.06
    include
    -0.06
    にな
    -0.06
    Cli
    -0.06
    POSITIVE LOGITS
     secret
    0.07
     Recursive
    0.06
     бел
    0.06
     salud
    0.06
     Whale
    0.06
    apı
    0.06
     Tibet
    0.06
     ощущ
    0.06
     TRANS
    0.06
    DUCTION
    0.06
    Activations Density 0.202%

    No Known Activations