© 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
    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. 30681
    Prev
    Next
    INDEX
    Explanations

    extraterrestrial

    np_max-act · gemini-2.0-flash

    This neuron detects references to extraterrestrial contexts or life beyond Earth (e.g. “outside,” “elsewhere,” “extraterrestrial,” “life,” etc.).

    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
     Firefox
    -0.06
    /js
    -0.06
     pago
    -0.06
    ambia
    -0.06
    Letter
    -0.06
    昇
    -0.06
     کام
    -0.06
    UsageId
    -0.06
    年龄
    -0.06
    allax
    -0.06
    POSITIVE LOGITS
     Flor
    0.07
     "::
    0.07
     kims
    0.06
    лина
    0.06
    stars
    0.06
    �
    0.06
    ],&
    0.06
    OKIE
    0.06
    getData
    0.06
    Geo
    0.06
    Activations Density 0.003%

    No Known Activations