© 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. 6405
    Prev
    Next
    INDEX
    Explanations

    -life

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the word “life” (especially as part of “pro-life” or related movement terminology).

    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
     sided
    -0.07
    ीध
    -0.07
    siniz
    -0.07
     savage
    -0.06
    licken
    -0.06
    isen
    -0.06
     zoo
    -0.06
    不
    -0.06
    。不
    -0.06
     theft
    -0.06
    POSITIVE LOGITS
     Tra
    0.07
     allowing
    0.07
    工作
    0.07
     snow
    0.07
     impover
    0.06
     تق
    0.06
    Similar
    0.06
     advocacy
    0.06
     arp
    0.06
    레이
    0.06
    Activations Density 0.011%

    No Known Activations