© 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. 89118
    Prev
    Next
    INDEX
    Explanations

    news events

    np_max-act · gemini-2.0-flash

    This neuron detects descriptions of security or law-enforcement emergency actions, especially school lockdowns and police responses in news‐style reporting.

    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
     AM
    -0.07
     Y
    -0.07
     Cad
    -0.07
    Mil
    -0.07
    Amazing
    -0.07
    -production
    -0.06
     Apprentice
    -0.06
     Components
    -0.06
    Ø
    -0.06
    otropic
    -0.06
    POSITIVE LOGITS
    IBUTES
    0.07
     kraj
    0.06
     пунк
    0.06
     Triumph
    0.06
    0.06
     нельзя
    0.06
    ertia
    0.06
    :true
    0.06
     примі
    0.06
     persist
    0.06
    Activations Density 0.057%

    No Known Activations