© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41701
    Prev
    Next
    INDEX
    Explanations

    Named entities / codes

    np_max-act · gemini-2.0-flash

    This neuron activates on capitalized, relatively uncommon proper names or titles (e.g. “Orion,” “Watkins,” “Stryker”), effectively detecting named-entity tokens.

    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
    descending
    -0.07
    LoginPage
    -0.06
    HomePage
    -0.06
    Disc
    -0.06
    айд
    -0.06
    .openg
    -0.06
    FETCH
    -0.06
    SCAN
    -0.06
    -home
    -0.06
    Spring
    -0.06
    POSITIVE LOGITS
    تماد
    0.06
    (',')↵
    0.06
    	work
    0.06
    重複
    0.06
     чт
    0.06
    AGENT
    0.06
     faculties
    0.06
     deut
    0.06
     раді
    0.06
    bé
    0.06
    Activations Density 0.185%

    No Known Activations