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

    Neuronpedia

    APICircuit 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. 40640
    Prev
    Next
    INDEX
    Explanations

    health measurements and guidelines

    np_max-act · gemini-2.0-flash

    information related to obesity and its health impacts.

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

    This neuron primarily activates on numeric tokens (measurements, percentages, and other numbers) in the text.

    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
    ウス
    -0.07
    黒
    -0.07
    iversal
    -0.07
    ongoose
    -0.06
     mệnh
    -0.06
    (".");↵
    -0.06
     Arist
    -0.06
    abras
    -0.06
     preorder
    -0.06
    mh
    -0.06
    POSITIVE LOGITS
     enjo
    0.08
    ergarten
    0.07
    "><?
    0.06
    .setView
    0.06
     unusually
    0.06
     způsobem
    0.06
     protect
    0.06
     tucked
    0.06
     mainBundle
    0.06
     Paulo
    0.06
    Activations Density 0.230%

    No Known Activations