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. 129544
    Prev
    Next
    INDEX
    Explanations

    Introduction to a topic

    np_max-act · gemini-2.0-flash

    This neuron activates on references to philosophical or existential discussion, especially mentions of thinkers (e.g., philosophers, theologians) and debate about life’s meaning.

    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
    AG
    -0.07
     hvis
    -0.06
     Jenny
    -0.06
    xCB
    -0.06
     ifs
    -0.06
    762
    -0.06
    IQ
    -0.06
    PackageName
    -0.06
     jelly
    -0.06
     UX
    -0.06
    POSITIVE LOGITS
    越
    0.06
     Raider
    0.06
     stuffed
    0.06
    =#
    0.06
     Ninja
    0.06
     anarch
    0.06
    girl
    0.06
    ंगठन
    0.06
     Qed
    0.06
    ‌شن
    0.06
    Activations Density 0.050%

    No Known Activations