Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41828
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron activates on virus strain or isolate identifiers—those alphanumeric type/location/ID/year labels (e.g. “A/Nanchang/8002/2009” or “USA/Iowa/16465/2013”).

    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
    オン
    -0.07
     Sean
    -0.07
     retaliation
    -0.06
     moderators
    -0.06
    emey
    -0.06
    형
    -0.06
    Declared
    -0.06
     Hour
    -0.06
    asto
    -0.06
    kt
    -0.06
    POSITIVE LOGITS
    WiFi
    0.07
     These
    0.07
     creamy
    0.07
     zw
    0.06
    .'</
    0.06
     worthy
    0.06
     uyum
    0.06
     
    ↵
    ↵
    0.06
    [cnt
    0.06
    ,'']]],↵
    0.06
    Activations Density 0.007%

    No Known Activations