© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91647
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    This neuron activates on inclusive, first-person plural framing—phrases like “let’s,” “we,” and similar collective calls or commentary in the text.

    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
    724
    -0.07
     preamble
    -0.06
     表
    -0.06
     rims
    -0.06
    .fade
    -0.06
    blade
    -0.06
     pill
    -0.06
    .bc
    -0.05
    $c
    -0.05
    totals
    -0.05
    POSITIVE LOGITS
    Sit
    0.07
     Hin
    0.07
     vieux
    0.07
     Recogn
    0.07
    riz
    0.07
    πη
    0.06
    Ana
    0.06
     اهل
    0.06
    орон
    0.06
    .Adam
    0.06
    Activations Density 0.160%

    No Known Activations