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. 42340
    Prev
    Next
    INDEX
    Explanations

    ulin

    np_max-act · gemini-2.0-flash

    medical terms related to diabetes and its associated complications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect mentions of insulin and insulin‐related metabolic terms (e.g. “insulin,” “insulinemia,” “insulin resistance”).

    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
     згод
    -0.06
     DataGridView
    -0.06
     StringField
    -0.06
    psz
    -0.06
    signIn
    -0.06
    .head
    -0.06
     spotřeb
    -0.06
     Scott
    -0.06
     pot
    -0.06
    وجود
    -0.06
    POSITIVE LOGITS
     momentum
    0.06
     çift
    0.06
    込み
    0.06
    炸
    0.06
     helfen
    0.06
     strlen
    0.06
     hed
    0.06
     향
    0.06
    Sy
    0.06
    prefs
    0.06
    Activations Density 0.002%

    No Known Activations