© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30610
    Prev
    Next
    INDEX
    Explanations

    medical case reports with numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on cardinal numbers and nearby words reporting how many cases or patients are described, i.e. it flags “n cases,” “n patients,” etc.

    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
     Testament
    -0.07
    _embeddings
    -0.07
    USED
    -0.06
     mirrors
    -0.06
    руд
    -0.06
     lords
    -0.06
    (stage
    -0.06
     guilty
    -0.06
    rive
    -0.06
    (Command
    -0.06
    POSITIVE LOGITS
    稍
    0.07
    _yaw
    0.07
    @email
    0.07
    0.07
     अभ
    0.06
    ​
    0.06
    Compra
    0.06
     Begin
    0.06
    youtu
    0.06
    virt
    0.06
    Activations Density 0.041%

    No Known Activations