© 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. 73654
    Prev
    Next
    INDEX
    Explanations

    attacks

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to mentions of violent incidents, especially words like “attack,” “attacks,” and “bombings.”

    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
     solved
    -0.06
     Puzzle
    -0.06
     fries
    -0.06
     diets
    -0.06
     Rest
    -0.06
    Bulk
    -0.06
    oud
    -0.06
    Flag
    -0.06
    ارت
    -0.06
    .unique
    -0.06
    POSITIVE LOGITS
     publi
    0.07
    ."','".$
    0.07
     العربية
    0.06
     آمریک
    0.06
    contenido
    0.06
    locale
    0.06
     발표
    0.06
    ihan
    0.06
    詳細
    0.06
    .forName
    0.06
    Activations Density 0.023%

    No Known Activations