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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84399
    Prev
    Next
    INDEX
    Explanations

    medical records

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric measurements (especially medical vitals and lab values with units).

    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
     ngại
    -0.07
    TURE
    -0.06
    Spoiler
    -0.06
    فال
    -0.06
    FixedSize
    -0.06
    خش
    -0.06
    tığ
    -0.06
    够
    -0.06
     TextInput
    -0.06
    .setFocus
    -0.06
    POSITIVE LOGITS
     Creat
    0.07
     introduce
    0.07
     gathered
    0.07
    允
    0.07
    139
    0.07
     exchanged
    0.07
     seams
    0.06
    02
    0.06
    .Price
    0.06
    edad
    0.06
    Activations Density 0.011%

    No Known Activations