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. 472
    Prev
    Next
    INDEX
    Explanations

    Israel and Palestine

    np_max-act · gemini-2.0-flash

    references to the historical and religious context of Israel in the Bible.

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

    This neuron fires on Biblical place names and geographical terms (ancient locations).

    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
     acı
    -0.07
     bude
    -0.06
    CONTROL
    -0.06
    neas
    -0.06
     Summers
    -0.06
    lossen
    -0.06
    Bur
    -0.06
    ピー
    -0.06
    TECTION
    -0.06
     ادبی
    -0.06
    POSITIVE LOGITS
     đất
    0.07
     TextBox
    0.06
    ................
    0.06
    柜
    0.06
     replace
    0.06
    ichTextBox
    0.06
     embody
    0.06
    	tile
    0.06
     Strategy
    0.06
                          ↵
    0.06
    Activations Density 0.004%

    No Known Activations