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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84557
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    technical terms related to molecular biology, specifically those concerning cloning, characterization, and expression of proteins and enzymes.

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

    The neuron responds primarily to the preposition “of.”

    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
    -feedback
    -0.06
    _NC
    -0.06
    ypse
    -0.06
    bble
    -0.06
    strain
    -0.06
    DAO
    -0.06
    Encryption
    -0.06
    culus
    -0.06
    tic
    -0.06
     worm
    -0.06
    POSITIVE LOGITS
     لد
    0.06
    lerimiz
    0.06
     komp
    0.06
     р
    0.06
    .permission
    0.06
    ’é
    0.06
     nghiên
    0.06
                                                   
    0.06
    ViewController
    0.06
     kullanımı
    0.06
    Activations Density 0.037%

    No Known Activations