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. 125910
    Prev
    Next
    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash

    This neuron spots expressions of positive enthusiasm or excitement, especially in the context of joining or praising an institution.

    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
     Vz
    -0.07
     CAL
    -0.07
     Ar
    -0.07
    ulators
    -0.06
     T
    -0.06
     Guys
    -0.06
    Editors
    -0.06
     Kes
    -0.06
    /javascript
    -0.06
     Dut
    -0.06
    POSITIVE LOGITS
    DataGridViewTextBoxColumn
    0.06
    เกม
    0.06
    535
    0.06
    وگر
    0.06
    ậc
    0.06
    Courier
    0.06
    ]--;↵
    0.06
    خبر
    0.06
    ों
    0.06
    relay
    0.06
    Activations Density 0.043%

    No Known Activations