© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56677
    Prev
    Next
    INDEX
    Explanations

    God and creation

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the Genesis creation narrative—especially mentions of “God,” “created,” and related first‐chapter terms.

    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
     řízení
    -0.08
     başladı
    -0.06
     Brom
    -0.06
    ота
    -0.06
     biện
    -0.06
     buff
    -0.06
     pepper
    -0.06
     대전
    -0.06
    _STOP
    -0.06
     Dien
    -0.06
    POSITIVE LOGITS
    .AppSettings
    0.06
     LogManager
    0.06
     superClass
    0.06
     gemacht
    0.06
    .xx
    0.06
    ология
    0.06
    생님
    0.06
    orary
    0.06
    "'↵
    0.06
     Cem
    0.06
    Activations Density 0.008%

    No Known Activations