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

    Neuronpedia

    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. 44650
    Prev
    Next
    INDEX
    Explanations

    academics

    np_max-act · gemini-2.0-flash

    scientific facts related to the possibility of life forms in extraterrestrial environments.

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

    This neuron fires on words naming scientific disciplines (e.g. “chemistry,” “physics”).

    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
     prosecute
    -0.07
    งก
    -0.06
    ected
    -0.06
    통
    -0.06
    假
    -0.06
    ensing
    -0.06
    _e
    -0.06
    cmp
    -0.06
    “And
    -0.06
     Sometimes
    -0.06
    POSITIVE LOGITS
     comunic
    0.07
     sắc
    0.07
    阶
    0.07
     connections
    0.07
    ивання
    0.06
     LATIN
    0.06
    opes
    0.06
     STREET
    0.06
    ắn
    0.06
    (expected
    0.06
    Activations Density 0.064%

    No Known Activations