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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 84789
    Prev
    Next
    INDEX
    Explanations

    fraud/scams

    np_max-act · gemini-2.0-flash

    This neuron highlights references to Medicare or health-care fraud schemes and related terminology.

    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
    ospel
    -0.06
     silicone
    -0.06
    #SBATCH
    -0.06
     Abdul
    -0.06
    Bob
    -0.06
     detachment
    -0.06
    (branch
    -0.05
     NT
    -0.05
     Ли
    -0.05
     Shib
    -0.05
    POSITIVE LOGITS
    іч
    0.08
    �다
    0.07
     видно
    0.07
    髪
    0.07
     fixation
    0.07
    pson
    0.07
     bás
    0.07
     casualties
    0.07
     __(
    0.06
    |.
    0.06
    Activations Density 0.034%

    No Known Activations