© 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. 73797
    Prev
    Next
    INDEX
    Explanations

    medical health

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens referring to healthcare data or information (e.g., “health,” “data,” “patient,” “records,” “information”).

    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
    愿
    -0.06
    anti
    -0.06
    periences
    -0.06
     Korea
    -0.06
     antenn
    -0.06
     quỹ
    -0.06
    ेव
    -0.06
    _appro
    -0.06
    artists
    -0.06
     Shiv
    -0.06
    POSITIVE LOGITS
    .setHeight
    0.06
    Highest
    0.06
    cpf
    0.06
     haystack
    0.06
     republican
    0.06
    (proj
    0.06
     mph
    0.06
     AVC
    0.06
    ???
    0.06
    TimeString
    0.06
    Activations Density 0.039%

    No Known Activations