Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55752
    Prev
    Next
    INDEX
    Explanations

    extremist group attacks

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect references to terrorism—names of extremist groups and terrorism‐related attacks or organizations.

    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
    .HOUR
    -0.07
    horse
    -0.07
    	progress
    -0.06
     число
    -0.06
    ([
    -0.06
    Bitte
    -0.06
    Histogram
    -0.06
    getProperty
    -0.06
    entů
    -0.06
    .getElementsByClassName
    -0.06
    POSITIVE LOGITS
     самостоятель
    0.08
     Bản
    0.07
     결
    0.06
     bottoms
    0.06
     अपन
    0.06
    طل
    0.06
     tentative
    0.06
    sar
    0.06
    _android
    0.06
    Assigned
    0.06
    Activations Density 0.013%

    No Known Activations