© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25236
    Prev
    Next
    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of vitamin K (and its specific forms or “K-dependent” factors) in biochemical or medical contexts.

    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
     Раз
    -0.07
    アップ
    -0.06
    .AutoSizeMode
    -0.06
    paint
    -0.06
    ALER
    -0.06
     disorder
    -0.06
    .writeObject
    -0.06
    GetComponent
    -0.06
     pazar
    -0.06
    див
    -0.06
    POSITIVE LOGITS
    _irq
    0.08
     Kota
    0.07
    .createElement
    0.07
     Conj
    0.06
     USING
    0.06
    uggested
    0.06
     kinh
    0.06
     issues
    0.06
    .jp
    0.06
    _mv
    0.06
    Activations Density 0.001%

    No Known Activations