© 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. 30546
    Prev
    Next
    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a patient’s prior medical history.

    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
    ani
    -0.06
     sizable
    -0.06
    опис
    -0.06
    brids
    -0.06
     SCM
    -0.06
     interpreting
    -0.06
     откры
    -0.06
    rea
    -0.06
    оло
    -0.06
    梅
    -0.05
    POSITIVE LOGITS
    MFLOAT
    0.07
    =W
    0.07
     dumps
    0.07
     }
    0.06
     اضافه
    0.06
    ww
    0.06
    합
    0.06
     tông
    0.06
    �
    0.06
     ),↵
    0.06
    Activations Density 0.013%

    No Known Activations