© 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. 91493
    Prev
    Next
    INDEX
    Explanations

    chronic, post-stroke conditions

    np_max-act · gemini-2.0-flash

    This neuron detects numerical expressions of time (e.g., durations in months or years) in clinical study descriptions.

    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
    Saving
    -0.07
    され
    -0.07
     tamaño
    -0.07
    esome
    -0.06
    ENO
    -0.06
    ढ़
    -0.06
    emoth
    -0.06
    +Sans
    -0.06
    ูก
    -0.06
    plx
    -0.06
    POSITIVE LOGITS
     strikeouts
    0.07
    .subplots
    0.07
    ่ก
    0.06
    website
    0.06
     irq
    0.06
    (Bytes
    0.06
    ครอบ
    0.06
     represent
    0.06
     expressed
    0.06
     февраля
    0.06
    Activations Density 0.018%

    No Known Activations