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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 85500
    Prev
    Next
    INDEX
    Explanations

    riots

    np_max-act · gemini-2.0-flash

    events or instances of communal violence or riots involving different religious or ethnic groups.

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

    This neuron responds to words and tokens related to large‐scale violent events—especially riots, communal clashes, looting, and associated violence.

    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
    rotein
    -0.07
     компанії
    -0.07
    Amy
    -0.07
    ジュ
    -0.06
    605
    -0.06
    уется
    -0.06
     mdl
    -0.06
    zig
    -0.06
    Ion
    -0.06
     artwork
    -0.06
    POSITIVE LOGITS
     entityManager
    0.07
    .Errors
    0.07
     पड़
    0.06
     Location
    0.06
    PostBack
    0.06
    (length
    0.06
     Crafts
    0.06
    uyến
    0.06
     bon
    0.06
     mortal
    0.06
    Activations Density 0.018%

    No Known Activations