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. 104358
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash

    The neuron responds to numerical pH specifications in methods sections, particularly detecting “pH 8.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    enzymes related to protein modification and catalysis.

    oai_token-act-pair · gpt-4o-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
     frail
    -0.07
    antically
    -0.06
    _fun
    -0.06
     etkili
    -0.06
     lively
    -0.06
    ail
    -0.06
    tracted
    -0.06
     wallets
    -0.06
     altro
    -0.06
    epend
    -0.06
    POSITIVE LOGITS
    _ValueChanged
    0.06
    8
    0.06
     PropertyChanged
    0.06
    uspendLayout
    0.06
    /XMLSchema
    0.06
    	Dim
    0.06
    Courier
    0.06
    Subview
    0.06
    -invalid
    0.06
    мів
    0.06
    Activations Density 0.002%

    No Known Activations