© 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. 12571
    Prev
    Next
    INDEX
    Explanations

    Demo

    np_max-act · gemini-2.0-flash

    the word “demo” (in any capitalization) scattered throughout 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
     William
    -0.08
    William
    -0.08
    Increase
    -0.07
     زبان
    -0.06
     fibre
    -0.06
     Brave
    -0.06
     sixth
    -0.06
     Subtract
    -0.06
     understands
    -0.06
    Search
    -0.06
    POSITIVE LOGITS
     demo
    0.12
     Demo
    0.11
    Demo
    0.11
    .demo
    0.11
     demos
    0.10
    demo
    0.09
    ENO
    0.08
     Dem
    0.08
     memo
    0.07
    .docker
    0.07
    Activations Density 0.005%

    No Known Activations